Apple M3 Max (40-core GPU), 64 GB: which models fit?

RTX 4090 RTX 5090 RTX 3090 RTX 4060 Ti (16 GB)RTX 5070 Ti Radeon RX 7900 XTX M4 Max 128 GB M3 Ultra 512 GB DGX Spark (128 GB)All devices

Apple Silicon Mac

Apple M3 Max (40-core GPU), 64 GB

Memory64 GB unifiedBandwidth400 GB/s vendor specPlanned for models48.0 GiB 75% of unified memoryFilesMLX Apple MLX format

Editorial pick · 64 GB MacsQwen3.8-27B MLX 8-bit All picks

Budget = file + KV cache + 1 GiB runtime + 0.5 GiB spare. Macs: 75% of memory. Details

35 models fit M3 Max 40c GPU · 64 GB · 8K context

Ranked by Artificial Analysis Intelligence Index, unranked models last. Arena is shown separately. How ranking works

Intelligence

Artificial Analysis Intelligence Index · top 10 models that fit M3 Max 40c GPU · 64 GB · higher is better

Qwen3.8-27B33.7
G9v3-39A5B (preview)21.8
NVIDIA Nemotron 3.5 Bolt 74B-A9B21.4
K2-Horizon-7B20.6
Qwen3.6-35B-A3B18.2
Muse Glimmer 30B17.5
K2-Horizon-3.7B15.6
Qwen3.5-9B13.3
Qwen3.5-4B13.1
NVIDIA Nemotron 3.5 Lightning 30B-A3B12.9

AA estimate

Generation speed

Tokens per second on M3 Max 40c GPU · 64 GB, best file for each of the same models · higher is better

Qwen3.5-4B~65.3
K2-Horizon-3.7B~62.4
G9v3-39A5B (preview)~60.3
Qwen3.6-35B-A3B~54.6
NVIDIA Nemotron 3.5 Lightning 30B-A3B~52.6
K2-Horizon-7B~35.1
NVIDIA Nemotron 3.5 Bolt 74B-A9B~33.5
Qwen3.5-9B~32.2
Qwen3.8-27B~11.4
Muse Glimmer 30B~10

MeasuredEstimated (~)

WeightsKV cacheRuntimeFreeMeasuredlinks to its sourceEstimatedshown with ~Unknownnever zero

Qwen3.8-27B

Qwen/Qwen3.8-27B

2026-08-1427B dense

AA index33.7rank #13

Arena1,441

Best file & memory

MLX 8-bit27.5 GiB fileFits · conditional

29.0 of 48.0 GiB+8K ctx · max ≈256K

Prompt~213 t/sEstimated

Generate~11.4 t/sEstimated

First token · 4K prompt~19 sEstimated

Memory budget

Weights file	27.48 GiB	mlx-community/Qwen3.8-27B-8bit · 6 files HF files
KV cache · 8K	0.50 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	28.98 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈256K tokens (native 256K).

Other MLX files

MLX 4-bit 15.0 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 3 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 33.7 Qwen3.8 27B (Xhigh) · Arena 1,441 · Model page

G9v3-39A5B (preview)

ai9stars/G9v3-39A5B

2026-08 (day unknown)39B · 5B active

AA index21.8 AA estimaterank #29

Arena—

Best file & memory

MLX 4-bit21.2 GiB fileFits

22.5 of 48.0 GiB8K ctx · max ≈128K

Prompt~669 t/sEstimated

Generate~60.3 t/sEstimated

First token · 4K prompt~6.1 sEstimated

Memory budget

Weights file	21.24 GiB	rapid-mlx/G9v3-39A5B-MLX-4bit · 5 files HF files
KV cache · 8K	0.30 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Accounted	22.53 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈128K tokens (native 128K).

Where the speeds come from

Prompt estimated from median of 10 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 8 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 21.8 AA estimate G9v3-39A5B · Arena unknown · Model page

NVIDIA Nemotron 3.5 Bolt 74B-A9B

nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16

2026-10-1574B · 9B active

AA index21.4rank #32

Arena—

Best file & memory

MLX 4-bit40.3 GiB fileFits · conditional

41.3 of 48.0 GiB+8K ctx · max ≈256K

Prompt~372 t/sEstimated

Generate~33.5 t/sEstimated

First token · 4K prompt~11 sEstimated

Memory budget

Weights file	40.29 GiB	rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-4bit · 9 files HF files
KV cache · 8K	0.06 GiB	BF16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	41.35 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈256K tokens (native 256K).

Other MLX files

MLX 8-bit 74.7 GiB · too big · files

Where the speeds come from

Prompt estimated from median of 10 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 8 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Sliding-window allocation is not established.
Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 21.4 Nemotron 3.5 Bolt 74B-A9B · Arena unknown · Model page

K2-Horizon-7B

IFM/K2-Horizon-7B

2026-09-03size unknown

AA index20.6rank #33

Arena—

Best file & memory

MLX 8-bit8.9 GiB fileFits

11.0 of 48.0 GiB8K ctx · max ≈267K

Prompt—Unknown

Generate~35.1 t/sEstimated

First token · 4K prompt—Unknown

Memory budget

Weights file	8.91 GiB	mlx-community/K2-Horizon-7B-8bit · 2 files HF files
KV cache · 8K	1.13 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Accounted	11.03 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈267K tokens (native 512K).

Other MLX files

MLX 4-bit 6.7 GiB · fits · files

Where the speeds come from

Prompt unknown: no measured report, and no comparable vendor FP16 figure or device calibration.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token unknown: needs a prefill value.

Caveats

Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 20.6 K2 Horizon 7B · Arena unknown · Model page

Qwen3.6-35B-A3B

Qwen/Qwen3.6-35B-A3B

2026-04-1635B · 3B active

AA index18.2rank #36

Arena—

Best file & memory

MLX 8-bit35.1 GiB fileFits · conditional

36.3 of 48.0 GiB+8K ctx · max ≈256K

Prompt~1,115 t/sEstimated

Generate~54.6 t/sEstimated

First token · 4K prompt~3.7 sEstimated

Memory budget

Weights file	35.13 GiB	mlx-community/Qwen3.6-35B-A3B-8bit · 8 files HF files
KV cache · 8K	0.16 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	36.29 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈256K tokens (native 256K).

Other MLX files

MLX 4-bit 19.0 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 10 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 8 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 18.2 Qwen3.6 35B A3B (Reasoning) · Arena unknown · Model page

Muse Glimmer 30B

meta-models/Muse-Glimmer-30B

2026-08-1030B dense

AA index17.5rank #38

Arena1,389

Best file & memory

MLX 8-bit31.1 GiB fileFits

32.3 of 48.0 GiB8K ctx · max ≈128K

Prompt~194 t/sEstimated

Generate~10 t/sEstimated

First token · 4K prompt~21 sEstimated

Memory budget

Weights file	31.08 GiB	mlx-community/Muse-Glimmer-30B-8bit · 153 files HF files
KV cache · 8K	0.18 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Accounted	32.26 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈128K tokens (native 128K).

Other MLX files

MLX 4-bit 18.1 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 3 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 17.5 Muse Glimmer (High) · Arena 1,389 · Model page

K2-Horizon-3.7B

IFM/K2-Horizon-3.7B

2026-09-03size unknown

AA index15.6rank #41

Arena—

Best file & memory

MLX 8-bit5.0 GiB fileFits

7.1 of 48.0 GiB8K ctx · max ≈295K

Prompt—Unknown

Generate~62.4 t/sEstimated

First token · 4K prompt—Unknown

Memory budget

Weights file	5.01 GiB	mlx-community/K2-Horizon-3.7B-8bit · 2 files HF files
KV cache · 8K	1.13 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Accounted	7.13 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈295K tokens (native 512K).

Other MLX files

MLX 4-bit 3.9 GiB · fits · files

Where the speeds come from

Prompt unknown: no measured report, and no comparable vendor FP16 figure or device calibration.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token unknown: needs a prefill value.

Caveats

Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 15.6 K2 Horizon 3.7B · Arena unknown · Model page

Qwen3.5-9B

Qwen/Qwen3.5-9B

2026-03-029B dense

AA index13.3 AA estimaterank #45

Arena—

Best file & memory

MLX 8-bit9.7 GiB fileFits · conditional

11.0 of 48.0 GiB+8K ctx · max ≈256K

Prompt~638 t/sEstimated

Generate~32.2 t/sEstimated

First token · 4K prompt~6.4 sEstimated

Memory budget

Weights file	9.71 GiB	mlx-community/Qwen3.5-9B-8bit · 2 files HF files
KV cache · 8K	0.25 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	10.96 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈256K tokens (native 256K).

Other MLX files

MLX 4-bit 5.5 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 3 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 13.3 AA estimate Qwen3.5 9B (Non-reasoning) · Arena unknown · Model page

Qwen3.5-4B

Qwen/Qwen3.5-4B

2026-03-024B dense

AA index13.1 AA estimaterank #48

Arena—

Best file & memory

MLX 8-bit4.8 GiB fileFits · conditional

6.0 of 48.0 GiB+8K ctx · max ≈256K

Prompt~1,436 t/sEstimated

Generate~65.3 t/sEstimated

First token · 4K prompt~2.9 sEstimated

Memory budget

Weights file	4.78 GiB	mlx-community/Qwen3.5-4B-8bit HF files
KV cache · 8K	0.25 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	6.03 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈256K tokens (native 256K).

Other MLX files

MLX 4-bit 2.8 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 3 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 13.1 AA estimate Qwen3.5 4B (Reasoning) · Arena unknown · Model page

NVIDIA Nemotron 3.5 Lightning 30B-A3B

nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16

2026-08-1130B · 3B active

AA index12.9rank #49

Arena1,329

Best file & memory

MLX 8-bit31.3 GiB fileFits · conditional

32.3 of 48.0 GiB+8K ctx · max ≈256K

Prompt~1,115 t/sEstimated

Generate~52.6 t/sEstimated

First token · 4K prompt~3.7 sEstimated

Memory budget

Weights file	31.26 GiB	mlx-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-8bit · 7 files HF files
KV cache · 8K	0.05 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	32.30 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈256K tokens (native 256K).

Other MLX files

MLX 4-bit 16.6 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 10 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 8 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 12.9 Nemotron 3.5 Lightning · Arena 1,329 · Model page

IBM Granite 4.2 30B

ibm-granite/granite-4.2-30b

2026-08-2530B dense

AA index12.7rank #50

Arena1,361

Best file & memory

MLX 8-bit29.0 GiB fileFits

32.0 of 48.0 GiB8K ctx · max ≈70K

Prompt~192 t/sEstimated

Generate~10.8 t/sEstimated

First token · 4K prompt~21 sEstimated

Memory budget

Weights file	28.97 GiB	lmstudio-community/granite-4.2-30b-MLX-8bit · 6 files HF files
KV cache · 8K	2.00 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Accounted	31.97 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈70K tokens (native 128K).

Other MLX files

MLX 4-bit 15.3 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 3 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 12.7 Granite 4.2 30B · Arena 1,361 · Model page

MiniCPM5-2B

openbmb/MiniCPM5-2B

2026-09-072.5B dense

AA index12.5rank #51

Arena—

Best file & memory

MLX 8-bit2.5 GiB fileFits

3.8 of 48.0 GiB8K ctx · max ≈128K

Prompt~2,283 t/sEstimated

Generate~125 t/sEstimated

First token · 4K prompt~1.8 sEstimated

Memory budget

Weights file	2.49 GiB	mlx-community/MiniCPM5-2B-8bit HF files
KV cache · 8K	0.33 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Accounted	3.82 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈128K tokens (native 128K).

Other MLX files

MLX 4-bit 1.3 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 3 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 12.5 MiniCPM5-2B · Arena unknown · Model page

Nemotron Cascade 2 30B A3B

nvidia/Nemotron-Cascade-2-30B-A3B

2026-03-1930B · 3B active

AA index11.7 AA estimaterank #53

Arena—

Best file & memory

MLX 8-bit31.3 GiB fileFits · conditional

32.3 of 48.0 GiB+8K ctx · max ≈256K

Prompt~1,115 t/sEstimated

Generate~52.6 t/sEstimated

First token · 4K prompt~3.7 sEstimated

Memory budget

Weights file	31.26 GiB	mlx-community/Nemotron-Cascade-2-30B-A3B-8bit · 7 files HF files
KV cache · 8K	0.05 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	32.30 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈256K tokens (native 256K).

Other MLX files

MLX 4-bit 16.6 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 10 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 8 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 11.7 AA estimate Nemotron Cascade 2 30B A3B · Arena unknown · Model page

Granite 4.2 8B

ibm-granite/granite-4.2-8b

2026-08-258B dense

AA index11.1rank #56

Arena1,320

Best file & memory

MLX 8-bit8.7 GiB fileFits

10.9 of 48.0 GiB8K ctx · max ≈128K

Prompt~718 t/sEstimated

Generate~35.9 t/sEstimated

First token · 4K prompt~5.7 sEstimated

Memory budget

Weights file	8.70 GiB	lmstudio-community/granite-4.2-8b-MLX-8bit · 2 files HF files
KV cache · 8K	1.25 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Accounted	10.95 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈128K tokens (native 128K).

Other MLX files

MLX 4-bit 4.6 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 3 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 11.1 Granite 4.2 8B · Arena 1,320 · Model page

G9v3-3B

AI9Stars/G9v3-3B

2026-07 (day unknown)3B dense

AA index10.8 AA estimaterank #58

Arena—

Best file & memory

MLX 4-bit1.6 GiB fileFits

3.0 of 48.0 GiB8K ctx · max ≈128K

Prompt~1,915 t/sEstimated

Generate~199 t/sEstimated

First token · 4K prompt~2.1 sEstimated

Memory budget

Weights file	1.57 GiB	cof139/G9v3-3B-mlx-4Bit HF files
KV cache · 8K	0.41 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Accounted	2.97 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈128K tokens (native 128K).

Where the speeds come from

Prompt estimated from median of 3 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 10.8 AA estimate G9v3-3B · Arena unknown · Model page

North Mini Code

CohereLabs/North-Mini-Code-1.0

2026-06-0930B · 3B active

AA index9.9rank #61

Arena—

Best file & memory

MLX 8-bit31.0 GiB fileFits

32.5 of 48.0 GiB8K ctx · max ≈250K

Prompt~1,115 t/sEstimated

Generate~53 t/sEstimated

First token · 4K prompt~3.7 sEstimated

Memory budget

Weights file	30.98 GiB	aaronmwelborn/North-Mini-Code-1.0-8bit · 7 files HF files
KV cache · 8K	0.48 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Accounted	32.47 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈250K tokens (native 250K).

Other MLX files

MLX 4-bit 17.2 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 10 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 8 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 9.9 North Mini Code · Arena unknown · Model page

Qwen3-Coder-Next

Qwen/Qwen3-Coder-Next

2026-02-0280B · 3B active

AA index9.2rank #63

Arena—

Best file & memory

MLX 4-bit41.8 GiB fileFits · conditional

43.0 of 48.0 GiB+8K ctx · max ≈202K

Prompt~1,115 t/sEstimated

Generate~105 t/sEstimated

First token · 4K prompt~3.7 sEstimated

Memory budget

Weights file	41.76 GiB	mlx-community/Qwen3-Coder-Next-4bit · 9 files HF files
KV cache · 8K	0.19 GiB	BF16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	42.95 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈202K tokens (native 256K).

Other MLX files

MLX 8-bit 78.8 GiB · too big · files

Where the speeds come from

Prompt estimated from median of 10 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 8 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 9.2 Qwen3 Coder Next · Arena unknown · Model page

Granite 4.2 3B

ibm-granite/granite-4.2-3b

2026-08-253B dense

AA index9.1rank #64

Arena1,293

Best file & memory

MLX 8-bit3.6 GiB fileFits

5.2 of 48.0 GiB8K ctx · max ≈128K

Prompt~1,915 t/sEstimated

Generate~86.2 t/sEstimated

First token · 4K prompt~2.1 sEstimated

Memory budget

Weights file	3.62 GiB	lmstudio-community/granite-4.2-3b-MLX-8bit HF files
KV cache · 8K	0.63 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Accounted	5.25 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈128K tokens (native 128K).

Other MLX files

MLX 4-bit 1.9 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 3 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 9.1 Granite 4.2 3B · Arena 1,293 · Model page

MiniCPM5-1B

openbmb/MiniCPM5-1B

2026-05-191.1B dense

AA index8.8 AA estimaterank #67

Arena—

Best file & memory

MLX 8-bit1.1 GiB fileFits

2.3 of 48.0 GiB8K ctx · max ≈128K

Prompt~5,316 t/sEstimated

Generate~292 t/sEstimated

First token · 4K prompt~770 msEstimated

Memory budget

Weights file	1.07 GiB	mlx-community/MiniCPM5-1B-8bit HF files
KV cache · 8K	0.19 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Accounted	2.26 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈128K tokens (native 128K).

Other MLX files

MLX 4-bit 0.6 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 3 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 8.8 AA estimate MiniCPM5-1B (Reasoning) · Arena unknown · Model page

Nanbeige4.1-3B

Nanbeige/Nanbeige4.1-3B

2026-02 (day unknown)3B dense

AA index8.4 AA estimaterank #69

Arena—

Best file & memory

MLX 8-bit3.9 GiB fileFits

5.4 of 48.0 GiB8K ctx · max ≈256K

Prompt~1,915 t/sEstimated

Generate~80.2 t/sEstimated

First token · 4K prompt~2.1 sEstimated

Memory budget

Weights file	3.89 GiB	mlx-community/Nanbeige4.1-3B-8bit HF files
KV cache · 8K	0.50 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Accounted	5.39 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈256K tokens (native 256K).

Other MLX files

MLX 4-bit 2.1 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 3 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 8.4 AA estimate Nanbeige4.1-3B · Arena unknown · Model page

LFM2.5-2.6B

LiquidAI/LFM2.5-2.6B

2026-08-042.7B dense

AA index8.4 AA estimaterank #70

Arena—

Best file & memory

MLX 8-bit2.7 GiB fileFits · conditional

3.8 of 48.0 GiB+8K ctx · max ≈128K

Prompt~2,136 t/sEstimated

Generate~117 t/sEstimated

First token · 4K prompt~1.9 sEstimated

Memory budget

Weights file	2.67 GiB	LiquidAI/LFM2.5-2.6B-MLX-8bit HF files
KV cache · 8K	0.13 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	3.79 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈128K tokens (native 128K).

Other MLX files

MLX 4-bit 1.5 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 3 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 8.4 AA estimate LFM2.5-2.6B · Arena unknown · Model page

Falcon-H1R-7B

tiiuae/Falcon-H1R-7B

2026-01-057B dense

AA index7.8 AA estimaterank #71

Arena—

Best file & memory

MLX 8-bit7.5 GiB fileFits · conditional

8.9 of 48.0 GiB+8K ctx · max ≈256K

Prompt~821 t/sEstimated

Generate~41.6 t/sEstimated

First token · 4K prompt~5.0 sEstimated

Memory budget

Weights file	7.51 GiB	mlx-community/Falcon-H1R-7B-8bit · 2 files HF files
KV cache · 8K	0.34 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	8.85 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈256K tokens (native 256K).

Other MLX files

MLX 4-bit 4.0 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 3 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 7.8 AA estimate Falcon-H1R-7B · Arena unknown · Model page

LFM2.5-8B-A1B

LiquidAI/LFM2.5-8B-A1B

2026-05-288.3B · 1.5B active

AA index7.2 AA estimaterank #74

Arena—

Best file & memory

MLX 8-bit8.4 GiB fileFits · conditional

9.5 of 48.0 GiB+8K ctx · max ≈125K

Prompt~2,230 t/sEstimated

Generate~108 t/sEstimated

First token · 4K prompt~1.8 sEstimated

Memory budget

Weights file	8.38 GiB	LiquidAI/LFM2.5-8B-A1B-MLX-8bit · 2 files HF files
KV cache · 8K	0.09 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	9.48 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈125K tokens (native 125K).

Other MLX files

MLX 4-bit 4.5 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 10 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 8 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 7.2 AA estimate LFM2.5-8B-A1B · Arena unknown · Model page

NVIDIA Nemotron 3 Nano 4B

nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16

2026-03-164B dense

AA index4.8rank #75

Arena—

Best file & memory

MLX 8-bit3.9 GiB fileFits · conditional

5.1 of 48.0 GiB+8K ctx · max ≈256K

Prompt~1,447 t/sEstimated

Generate~79.4 t/sEstimated

First token · 4K prompt~2.8 sEstimated

Memory budget

Weights file	3.93 GiB	mlx-community/NVIDIA-Nemotron-3-Nano-4B-8bit HF files
KV cache · 8K	0.13 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	5.06 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈256K tokens (native 256K).

Other MLX files

MLX 4-bit 2.1 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 3 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 4.8 NVIDIA Nemotron 3 Nano 4B · Arena unknown · Model page

LFM2.5-24B-A2B

LiquidAI/LFM2.5-24B-A2B

2026-10-1324B · 2B active

AA index—unranked

Arena—

Best file & memory

MLX 8-bit23.7 GiB fileFits · conditional

24.9 of 48.0 GiB+8K ctx · max ≈128K

Prompt~1,672 t/sEstimated

Generate~83.1 t/sEstimated

First token · 4K prompt~2.4 sEstimated

Memory budget

Weights file	23.73 GiB	LiquidAI/LFM2.5-24B-A2B-MLX-8bit · 5 files HF files
KV cache · 8K	0.16 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	24.89 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈128K tokens (native 128K).

Other MLX files

MLX 4-bit 12.6 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 10 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 8 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA index unknown · Arena unknown · Model page

MiniCPM-V 4.7 35B-A3B

openbmb/MiniCPM-V-4.7-35B-A3B

2026-10-1235B · 3B active

AA index—unranked

Arena—

Best file & memory

MLX 8-bit37.1 GiB fileFits · conditional

38.3 of 48.0 GiB+8K ctx · max ≈256K

Prompt~1,115 t/sEstimated

Generate~51.7 t/sEstimated

First token · 4K prompt~3.7 sEstimated

Memory budget

Weights file	37.10 GiB	mlx-community/MiniCPM-V-4.7-35B-A3B-8bit · 8 files HF files
KV cache · 8K	0.16 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	38.25 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈256K tokens (native 256K).

Other MLX files

MLX 4-bit 21.9 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 10 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 8 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA index unknown · Arena unknown · Model page

Aleph Alpha Kolibri-1

Aleph-Alpha/Kolibri-1

2026-10-0378B · 3.5B active

AA index—unranked

Arena—

Best file & memory

MLX 4-bit41.3 GiB fileFits · conditional

42.5 of 48.0 GiB+8K ctx · max ≈256K

Prompt~967 t/sEstimated

Generate~89.7 t/sEstimated

First token · 4K prompt~4.2 sEstimated

Memory budget

Weights file	41.29 GiB	velaia/Kolibri-1-MLX-4bit · 9 files HF files
KV cache · 8K	0.20 GiB	BF16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	42.48 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈256K tokens (native 256K).

Where the speeds come from

Prompt estimated from median of 10 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 8 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA index unknown · Arena unknown · Model page

MiMo-V2.6-Distill-Qwen-9B

XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B

2026-09-229B dense

AA index—unranked

Arena—

Best file & memory

MLX 8-bit9.7 GiB fileFits · conditional

11.0 of 48.0 GiB+8K ctx · max ≈256K

Prompt~638 t/sEstimated

Generate~32.2 t/sEstimated

First token · 4K prompt~6.4 sEstimated

Memory budget

Weights file	9.71 GiB	nativ-community/MiMo-V2.6-Distill-Qwen-9B-MLX-8bit · 2 files HF files
KV cache · 8K	0.25 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	10.96 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈256K tokens (native 256K).

Other MLX files

MLX 4-bit 5.5 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 3 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA index unknown · Arena unknown · Model page

K2-Horizon-0.9B

IFM/K2-Horizon-0.9B

2026-09-03size unknown

AA index—unranked

Arena—

Best file & memory

MLX 8-bit1.1 GiB fileFits

2.5 of 48.0 GiB8K ctx · max ≈128K

Prompt—Unknown

Generate~293 t/sEstimated

First token · 4K prompt—Unknown

Memory budget

Weights file	1.07 GiB	mlx-community/K2-Horizon-0.9B-8bit HF files
KV cache · 8K	0.44 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Accounted	2.50 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈128K tokens (native 128K).

Other MLX files

MLX 4-bit 0.8 GiB · fits · files

Where the speeds come from

Prompt unknown: no measured report, and no comparable vendor FP16 figure or device calibration.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token unknown: needs a prefill value.

Caveats

Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA index unknown · Arena unknown · Model page

Ornith-1.5-9B

ornith-ai/Ornith-1.5-9B

2026-08 (day unknown)9B dense

AA index—unranked

Arena—

Best file & memory

MLX 8-bit8.9 GiB fileFits · conditional

10.1 of 48.0 GiB+8K ctx · max ≈256K

Prompt~638 t/sEstimated

Generate~35.3 t/sEstimated

First token · 4K prompt~6.4 sEstimated

Memory budget

Weights file	8.86 GiB	ornith-ai/Ornith-1.5-9B-MLX-8bit · 2 files HF files
KV cache · 8K	0.25 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	10.11 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈256K tokens (native 256K).

Other MLX files

MLX 4-bit 4.7 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 3 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA index unknown · Arena unknown · Model page

Qwen3.6-27B

Qwen/Qwen3.6-27B

2026-04-2227B dense

AA index—unranked

Arena—

Best file & memory

MLX 8-bit27.5 GiB fileFits · conditional

29.0 of 48.0 GiB+8K ctx · max ≈256K

Prompt~213 t/sEstimated

Generate~11.4 t/sEstimated

First token · 4K prompt~19 sEstimated

Memory budget

Weights file	27.48 GiB	mlx-community/Qwen3.6-27B-8bit · 6 files HF files
KV cache · 8K	0.50 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	28.98 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈256K tokens (native 256K).

Other MLX files

MLX 4-bit 15.0 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 3 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA index unknown · Arena unknown · Model page

Qwen3.5-0.8B

Qwen/Qwen3.5-0.8B

2026-03-020.8B dense

AA index—unranked

Arena—

Best file & memory

MLX 8-bit0.9 GiB fileFits · conditional

2.0 of 48.0 GiB+8K ctx · max ≈256K

Prompt~7,181 t/sEstimated

Generate~335 t/sEstimated

First token · 4K prompt~570 msEstimated

Memory budget

Weights file	0.93 GiB	mlx-community/Qwen3.5-0.8B-8bit HF files
KV cache · 8K	0.09 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	2.03 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈256K tokens (native 256K).

Other MLX files

MLX 4-bit 0.6 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 3 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA index unknown · Arena unknown · Model page

Qwen3.5-2B

Qwen/Qwen3.5-2B

2026-03-022B dense

AA index—unranked

Arena—

Best file & memory

MLX 8-bit2.5 GiB fileFits · conditional

3.6 of 48.0 GiB+8K ctx · max ≈256K

Prompt~2,873 t/sEstimated

Generate~126 t/sEstimated

First token · 4K prompt~1.4 sEstimated

Memory budget

Weights file	2.48 GiB	mlx-community/Qwen3.5-2B-8bit HF files
KV cache · 8K	0.09 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	3.57 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈256K tokens (native 256K).

Other MLX files

MLX 4-bit 1.6 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 3 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA index unknown · Arena unknown · Model page

Qwen3.5-27B

Qwen/Qwen3.5-27B

2026-02-2427B dense

AA index—unranked

Arena—

Best file & memory

MLX 8-bit27.5 GiB fileFits · conditional

29.0 of 48.0 GiB+8K ctx · max ≈256K

Prompt~213 t/sEstimated

Generate~11.4 t/sEstimated

First token · 4K prompt~19 sEstimated

Memory budget

Weights file	27.48 GiB	mlx-community/Qwen3.5-27B-8bit · 6 files HF files
KV cache · 8K	0.50 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	28.98 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈256K tokens (native 256K).

Other MLX files

MLX 4-bit 15.0 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 3 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA index unknown · Arena unknown · Model page

Qwen3.5-35B-A3B

Qwen/Qwen3.5-35B-A3B

2026-02-2435B · 3B active

AA index—unranked

Arena—

Best file & memory

MLX 8-bit35.1 GiB fileFits · conditional

36.3 of 48.0 GiB+8K ctx · max ≈256K

Prompt~1,115 t/sEstimated

Generate~54.6 t/sEstimated

First token · 4K prompt~3.7 sEstimated

Memory budget

Weights file	35.13 GiB	mlx-community/Qwen3.5-35B-A3B-8bit · 8 files HF files
KV cache · 8K	0.16 GiB	FP16 cache from config.json Estimated
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	36.29 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈256K tokens (native 256K).

Other MLX files

MLX 4-bit 19.0 GiB · fits · files

Where the speeds come from

Prompt estimated from median of 10 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 8 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA index unknown · Arena unknown · Model page

May fit: KV-cache size unknown 11

Weights and runtime fit, but the cache for this attention type is not established. Ranked by AA index.

K2-Horizon-MoVA-36B-A4B

IFM/K2-Horizon-MoVA-36B-A4B

2026-09-0336B · 4B active

AA index25.3rank #22

Arena—

Best file & memory

MLX 8-bit37.1 GiB fileCache unknown

38.1 of 48.0 GiB+8K ctx

Prompt~836 t/sEstimated

Generate~39.9 t/sEstimated

First token · 4K prompt~4.9 sEstimated

Memory budget

Weights file	37.07 GiB	mlx-community/K2-Horizon-MoVA-36B-A4B-8bit · 8 files HF files
KV cache · 8K	—	Unknown
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	38.07 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: unknown (native 512K).

Other MLX files

MLX 4-bit 24.6 GiB · cache unknown · files

Where the speeds come from

Prompt estimated from median of 10 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 8 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

KV-cache size could not be established from the config (compressed or backend-specific attention).
Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 25.3 K2 Horizon MoVA 36B A4B · Arena unknown · Model page

Gemma 4 26B A4B (it)

google/gemma-4-26B-A4B-it

2026-04-0225B · 3.8B active

AA index16.7 AA estimaterank #39

Arena1,434

Best file & memory

MLX 8-bit26.0 GiB fileCache unknown

27.0 of 48.0 GiB+8K ctx

Prompt~880 t/sEstimated

Generate~41.8 t/sEstimated

First token · 4K prompt~4.7 sEstimated

Memory budget

Weights file	26.03 GiB	mlx-community/gemma-4-26B-A4B-it-8bit · 6 files HF files
KV cache · 8K	—	Unknown
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	27.03 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: unknown (native 256K).

Other MLX files

MLX 4-bit 14.3 GiB · cache unknown · files

Where the speeds come from

Prompt estimated from median of 10 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 8 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

KV-cache size could not be established from the config (compressed or backend-specific attention).
Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 16.7 AA estimate Gemma 4 26B A4B (Reasoning) · Arena 1,434 · Model page

Gemma 4 31B (it)

google/gemma-4-31B-it

2026-04-0231B dense

AA index14.7rank #42

Arena1,443

Best file & memory

MLX 8-bit31.4 GiB fileCache unknown

32.4 of 48.0 GiB+8K ctx

Prompt~187 t/sEstimated

Generate~9.9 t/sEstimated

First token · 4K prompt~22 sEstimated

Memory budget

Weights file	31.44 GiB	mlx-community/gemma-4-31B-it-8bit · 7 files HF files
KV cache · 8K	—	Unknown
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	32.44 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: unknown (native 256K).

Other MLX files

MLX 4-bit 17.1 GiB · cache unknown · files

Where the speeds come from

Prompt estimated from median of 3 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

KV-cache size could not be established from the config (compressed or backend-specific attention).
Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 14.7 Gemma 4 31B (Reasoning) · Arena 1,443 · Model page

Gemma 4 12B (it)

google/gemma-4-12B-it

2026-06-0312B dense

AA index14.2 AA estimaterank #44

Arena—

Best file & memory

MLX 8-bit11.8 GiB fileCache unknown

12.8 of 48.0 GiB+8K ctx

Prompt~481 t/sEstimated

Generate~26.4 t/sEstimated

First token · 4K prompt~8.5 sEstimated

Memory budget

Weights file	11.84 GiB	mlx-community/gemma-4-12B-it-8bit · 3 files HF files
KV cache · 8K	—	Unknown
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	12.84 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: unknown (native 256K).

Other MLX files

MLX 4-bit 6.3 GiB · cache unknown · files

Where the speeds come from

Prompt estimated from median of 3 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

KV-cache size could not be established from the config (compressed or backend-specific attention).
Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 14.2 AA estimate Gemma 4 12B (Reasoning) · Arena unknown · Model page

LongCat-Flash-Lite

meituan-longcat/LongCat-Flash-Lite

2026-01 (day unknown)69B · 3B active

AA index11.5 AA estimaterank #54

Arena—

Best file & memory

MLX 4-bit35.9 GiB fileCache unknown

36.9 of 48.0 GiB+8K ctx

Prompt~1,115 t/sEstimated

Generate~104 t/sEstimated

First token · 4K prompt~3.7 sEstimated

Memory budget

Weights file	35.93 GiB	mlx-community/LongCat-Flash-Lite-4bit · 8 files HF files
KV cache · 8K	—	Unknown
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	36.93 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: unknown (native 320K).

Other MLX files

MLX 8-bit 67.8 GiB · too big · files

Where the speeds come from

Prompt estimated from median of 10 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 8 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

KV-cache size could not be established from the config (compressed or backend-specific attention).
Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 11.5 AA estimate LongCat Flash Lite · Arena unknown · Model page

Ling-3.0-tiny

inclusionAI/Ling-3.0-tiny

2026-08 (day unknown)7.9B · 1.3B active

AA index11.1rank #57

Arena—

Best file & memory

MLX 4-bit4.1 GiB fileCache unknown

5.1 of 48.0 GiB+8K ctx

Prompt~2,573 t/sEstimated

Generate~241 t/sEstimated

First token · 4K prompt~1.6 sEstimated

Memory budget

Weights file	4.14 GiB	rapid-mlx/Ling-3.0-tiny-MLX-4bit HF files
KV cache · 8K	—	Unknown
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	5.14 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: unknown (native 128K).

Where the speeds come from

Prompt estimated from median of 10 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 8 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

KV-cache size could not be established from the config (compressed or backend-specific attention).
Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 11.1 Ling 3.0 Tiny · Arena unknown · Model page

Nemotron 3 Nano Omni 30B A3B Reasoning

nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16

2026-04-2830B · 3B active

AA index10.3 AA estimaterank #60

Arena—

Best file & memory

MLX 8-bit33.3 GiB fileCache unknown

34.3 of 48.0 GiB+8K ctx

Prompt~1,115 t/sEstimated

Generate~49.3 t/sEstimated

First token · 4K prompt~3.7 sEstimated

Memory budget

Weights file	33.32 GiB	mlx-community/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-8bit · 8 files HF files
KV cache · 8K	—	Unknown
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	34.32 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: unknown (native 256K).

Other MLX files

MLX 4-bit 18.3 GiB · cache unknown · files

Where the speeds come from

Prompt estimated from median of 10 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 8 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

KV-cache size could not be established from the config (compressed or backend-specific attention).
Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 10.3 AA estimate Nemotron 3 Nano Omni 30B A3B Reasoning · Arena unknown · Model page

DiffusionGemma 26B A4B

google/diffusiongemma-26B-A4B-it

2026-06-1025B · 3.8B active

AA index9.5 AA estimaterank #62

Arena—

Best file & memory

MLX 8-bit26.1 GiB fileCache unknown

27.1 of 48.0 GiB+8K ctx

Prompt~880 t/sEstimated

Generate~41.8 t/sEstimated

First token · 4K prompt~4.7 sEstimated

Memory budget

Weights file	26.05 GiB	mlx-community/diffusiongemma-26B-A4B-it-8bit · 6 files HF files
KV cache · 8K	—	Unknown
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	27.05 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: unknown (native 256K).

Other MLX files

MLX 4-bit 15.4 GiB · cache unknown · files

Where the speeds come from

Prompt estimated from median of 10 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 8 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

KV-cache size could not be established from the config (compressed or backend-specific attention).
Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 9.5 AA estimate DiffusionGemma 26B A4B · Arena unknown · Model page

Gemma 4 E4B (it)

google/gemma-4-E4B-it

2026-04-028B dense

AA index8.9rank #66

Arena—

Best file & memory

MLX 8-bit8.3 GiB fileCache unknown

9.3 of 48.0 GiB+8K ctx

Prompt~718 t/sEstimated

Generate~37.8 t/sEstimated

First token · 4K prompt~5.7 sEstimated

Memory budget

Weights file	8.27 GiB	mlx-community/gemma-4-E4B-it-8bit · 2 files HF files
KV cache · 8K	—	Unknown
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	9.27 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: unknown (native 128K).

Other MLX files

MLX 4-bit 4.8 GiB · cache unknown · files

Where the speeds come from

Prompt estimated from median of 3 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

KV-cache size could not be established from the config (compressed or backend-specific attention).
Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 8.9 Gemma 4 E4B (Reasoning) · Arena unknown · Model page

Gemma 4 E2B

google/gemma-4-E2B-it

2026-04-025.1B dense

AA index7.8 AA estimaterank #72

Arena—

Best file & memory

MLX 8-bit5.5 GiB fileCache unknown

6.5 of 48.0 GiB+8K ctx

Prompt~1,126 t/sEstimated

Generate~57.2 t/sEstimated

First token · 4K prompt~3.6 sEstimated

Memory budget

Weights file	5.46 GiB	mlx-community/gemma-4-E2B-it-8bit · 2 files HF files
KV cache · 8K	—	Unknown
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	6.46 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: unknown (native 128K).

Other MLX files

MLX 4-bit 3.3 GiB · cache unknown · files

Where the speeds come from

Prompt estimated from median of 3 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 3 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

KV-cache size could not be established from the config (compressed or backend-specific attention).
Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA 7.8 AA estimate Gemma 4 E2B (Reasoning) · Arena unknown · Model page

GLM-4.7-Flash

zai-org/GLM-4.7-Flash

2026-01 (day unknown)30B · 3B active

AA index—unranked

Arena—

Best file & memory

MLX 8-bit29.6 GiB fileCache unknown

30.6 of 48.0 GiB+8K ctx

Prompt~1,115 t/sEstimated

Generate~55.4 t/sEstimated

First token · 4K prompt~3.7 sEstimated

Memory budget

Weights file	29.64 GiB	mlx-community/GLM-4.7-Flash-8bit · 7 files HF files
KV cache · 8K	—	Unknown
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	30.64 GiB	of 48.0 GiB usable (75% of 64 GB) · 0.5 GiB spare margin required

Max context in free memory: unknown (native 198K).

Other MLX files

MLX 4-bit 15.7 GiB · cache unknown · files

Where the speeds come from

Prompt estimated from median of 10 measured prefill points for this device (MLX), rescaled to this model.
Generate estimated from median of 8 measured decode points for this device (MLX), rescaled to this model.
First token 4K-token prompt ÷ estimated prefill speed. Excludes model load and queueing.

Caveats

KV-cache size could not be established from the config (compressed or backend-specific attention).
Fixed recurrent/convolution state is unknown and not included.
Text-only budget. A downloadable file does not prove your runtime supports this architecture.

AA index unknown · Arena unknown · Model page

25 models too big for M3 Max 40c GPU · 64 GB

GLM-5.3-FlashMLX 4-bit needs 191 GiB+ (KV unknown)
Qwen3.8-Flash-NextMLX 4-bit needs 105 GiB+ (KV unknown)
Muse Spark Open (816B-A42B)MLX 4-bit needs 498 GiB+ (KV unknown)
Motif 3MLX 8-bit needs 313 GiB+ (KV unknown)
MiniMax-M3MLX 4-bit needs 226 GiB+ (KV unknown)
Nex-N2-Pro (Qwen3.5-397B-A17B based)MLX 8-bit needs 394 GiB
NVIDIA Nemotron 3.5 Super VL 120B-A12BMLX 4-bit needs 66.2 GiB
Kimi K2.7 CodeMLX 4-bit needs 598 GiB+ (KV unknown)
Inkling-SmallMLX 4-bit needs 145 GiB
InklingMLX 4-bit needs 513 GiB
Solar Open 2 (250B-A15B)MLX 4-bit needs 133 GiB
NVIDIA Nemotron 3 Ultra 550B-A55BMLX 4-bit needs 290 GiB
Qwen3.5-397B-A17BMLX 4-bit needs 210 GiB
Qwen3.5-122B-A10BMLX 4-bit needs 66.5 GiB
Mistral Medium 3.5 (128B dense)MLX 4-bit needs 76.9 GiB
Trinity-Large-ThinkingMLX 4-bit needs 212 GiB
Hy4-previewMLX 4-bit needs 405 GiB+ (KV unknown)
Ling-3.0-flashMLX 4-bit needs 66.7 GiB+ (KV unknown)
DeepSeek V4 Flash 0731MLX 4-bit needs 145 GiB+ (KV unknown)
Poolside Laguna S 2.1MLX 4-bit needs 63.6 GiB
GLM-5.2MLX 4-bit needs 391 GiB+ (KV unknown)
Step 3.7 FlashMLX 4-bit needs 105 GiB+ (KV unknown)
Kimi K2.6MLX 4-bit needs 614 GiB+ (KV unknown)
NVIDIA Nemotron 3 Super 120B-A12BMLX 4-bit needs 64.9 GiB
MiniMax-M2.7MLX 4-bit needs 123 GiB

Specs & sources

Memory	64 GB unified	source
Bandwidth	400 GB/s	source
FP16	unknown	Apple publishes no comparable FP16 throughput or GPU-only TDP in reviewed chip/device technical specifications. Power adapter rating and whole-system maximum continuous power are not GPU TDP.
Power	unknown	Apple publishes no comparable FP16 throughput or GPU-only TDP in reviewed chip/device technical specifications. Power adapter rating and whole-system maximum continuous power are not GPU TDP.

Found in: MacBook Pro (14-inch, M3 Pro or M3 Max, 2023)

Measured speeds

29 reported observations

On this device (same chip and GPU-core count). Reported by the linked sources; not reproduced by LocalFit.

Open in speed database Submit yours

Doesn't fit? Rent a GPU

RunpodPlaceholderCloud GPU pods you can rent for running larger models.
Vast.aiPlaceholderGPU rental marketplace with many hosts and GPU types.
LambdaPlaceholderCloud GPU instances for AI training and inference.
TensorDockPlaceholderGPU cloud marketplace with consumer and datacenter GPUs.

Sponsored placeholder links: LocalFit may earn a commission if these become affiliate links. They never influence fit results, estimates or picks.