Apple M2 (10-core GPU), 16 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 M2 (10-core GPU), 16 GB

Memory16 GB unifiedBandwidth100 GB/s vendor specPlanned for models12.0 GiB 75% of unified memoryFilesMLX Apple MLX format

Editorial pick · 16 GB MacsK2-Horizon-7B MLX 8-bit All picks

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

19 models fit M2 10c GPU · 16 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 M2 10c GPU · 16 GB · higher is better

AA estimate

Generation speed

Tokens per second on M2 10c GPU · 16 GB, best file for each of the same models · higher is better

MeasuredEstimated (~)

WeightsKV cacheRuntimeFreeMeasuredlinks to its sourceEstimatedshown with ~Unknownnever zero

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 12.0 GiB8K ctx · max ≈11K

Prompt—Unknown

Generate~8.6 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 12.0 GiB usable (75% of 16 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈11K 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 MLX median efficiency 0.8231 (n=60) × memory bandwidth ÷ 8.9 GiB read per token.
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

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 12.0 GiB8K ctx · max ≈39K

Prompt—Unknown

Generate~15.3 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 12.0 GiB usable (75% of 16 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈39K 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 MLX median efficiency 0.8231 (n=60) × memory bandwidth ÷ 5.0 GiB read per token.
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 12.0 GiB+8K ctx · max ≈25K

Prompt~98.7 t/sEstimated

Generate~7.9 t/sEstimated

First token · 4K prompt~42 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 12.0 GiB usable (75% of 16 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈25K tokens (native 256K).

Other MLX files

MLX 4-bit 5.5 GiB · fits · files

Where the speeds come from

Prompt estimated from median prefill rate per GPU core of 11 measured M2 points (MLX) × this chip's GPU cores ÷ (2 × active params).
Generate estimated from MLX median efficiency 0.8231 (n=60) × memory bandwidth ÷ 9.7 GiB read per token.
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 12.0 GiB+8K ctx · max ≈183K

Prompt~222 t/sEstimated

Generate~16 t/sEstimated

First token · 4K prompt~18 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 12.0 GiB usable (75% of 16 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈183K tokens (native 256K).

Other MLX files

MLX 4-bit 2.8 GiB · fits · files

Where the speeds come from

Prompt estimated from median prefill rate per GPU core of 11 measured M2 points (MLX) × this chip's GPU cores ÷ (2 × active params).
Generate estimated from MLX median efficiency 0.8231 (n=60) × memory bandwidth ÷ 4.8 GiB read per token.
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

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 12.0 GiB8K ctx · max ≈128K

Prompt~353 t/sEstimated

Generate~30.8 t/sEstimated

First token · 4K prompt~12 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 12.0 GiB usable (75% of 16 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 prefill rate per GPU core of 11 measured M2 points (MLX) × this chip's GPU cores ÷ (2 × active params).
Generate estimated from MLX median efficiency 0.8231 (n=60) × memory bandwidth ÷ 2.5 GiB read per token.
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

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 12.0 GiB8K ctx · max ≈12K

Prompt~111 t/sEstimated

Generate~8.8 t/sEstimated

First token · 4K prompt~37 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 12.0 GiB usable (75% of 16 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈12K tokens (native 128K).

Other MLX files

MLX 4-bit 4.6 GiB · fits · files

Where the speeds come from

Prompt estimated from median prefill rate per GPU core of 11 measured M2 points (MLX) × this chip's GPU cores ÷ (2 × active params).
Generate estimated from MLX median efficiency 0.8231 (n=60) × memory bandwidth ÷ 8.7 GiB read per token.
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 12.0 GiB8K ctx · max ≈128K

Prompt~296 t/sEstimated

Generate~48.9 t/sEstimated

First token · 4K prompt~14 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 12.0 GiB usable (75% of 16 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 prefill rate per GPU core of 11 measured M2 points (MLX) × this chip's GPU cores ÷ (2 × active params).
Generate estimated from MLX median efficiency 0.8231 (n=60) × memory bandwidth ÷ 1.6 GiB read per token.
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

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 12.0 GiB8K ctx · max ≈88K

Prompt~296 t/sEstimated

Generate~21.2 t/sEstimated

First token · 4K prompt~14 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 12.0 GiB usable (75% of 16 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈88K tokens (native 128K).

Other MLX files

MLX 4-bit 1.9 GiB · fits · files

Where the speeds come from

Prompt estimated from median prefill rate per GPU core of 11 measured M2 points (MLX) × this chip's GPU cores ÷ (2 × active params).
Generate estimated from MLX median efficiency 0.8231 (n=60) × memory bandwidth ÷ 3.6 GiB read per token.
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 12.0 GiB8K ctx · max ≈128K

Prompt~822 t/sEstimated

Generate~71.7 t/sEstimated

First token · 4K prompt~5.0 sEstimated

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 12.0 GiB usable (75% of 16 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 prefill rate per GPU core of 11 measured M2 points (MLX) × this chip's GPU cores ÷ (2 × active params).
Generate estimated from MLX median efficiency 0.8231 (n=60) × memory bandwidth ÷ 1.1 GiB read per token.
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 12.0 GiB8K ctx · max ≈106K

Prompt~296 t/sEstimated

Generate~19.7 t/sEstimated

First token · 4K prompt~14 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 12.0 GiB usable (75% of 16 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈106K tokens (native 256K).

Other MLX files

MLX 4-bit 2.1 GiB · fits · files

Where the speeds come from

Prompt estimated from median prefill rate per GPU core of 11 measured M2 points (MLX) × this chip's GPU cores ÷ (2 × active params).
Generate estimated from MLX median efficiency 0.8231 (n=60) × memory bandwidth ÷ 3.9 GiB read per token.
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 12.0 GiB+8K ctx · max ≈128K

Prompt~330 t/sEstimated

Generate~28.7 t/sEstimated

First token · 4K prompt~12 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 12.0 GiB usable (75% of 16 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 prefill rate per GPU core of 11 measured M2 points (MLX) × this chip's GPU cores ÷ (2 × active params).
Generate estimated from MLX median efficiency 0.8231 (n=60) × memory bandwidth ÷ 2.7 GiB read per token.
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 12.0 GiB+8K ctx · max ≈70K

Prompt~127 t/sEstimated

Generate~10.2 t/sEstimated

First token · 4K prompt~32 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 12.0 GiB usable (75% of 16 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈70K tokens (native 256K).

Other MLX files

MLX 4-bit 4.0 GiB · fits · files

Where the speeds come from

Prompt estimated from median prefill rate per GPU core of 11 measured M2 points (MLX) × this chip's GPU cores ÷ (2 × active params).
Generate estimated from MLX median efficiency 0.8231 (n=60) × memory bandwidth ÷ 7.5 GiB read per token.
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 12.0 GiB+8K ctx · max ≈125K

Prompt~365 t/sEstimated

Generate~21 t/sEstimated

First token · 4K prompt~11 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 12.0 GiB usable (75% of 16 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 prefill rate per GPU core of 21 measured M2 points (MLX) × this chip's GPU cores ÷ (2 × active params).
Generate estimated from MLX median efficiency 0.3416 (n=94) × memory bandwidth ÷ 1.5 GiB read per token.
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 12.0 GiB+8K ctx · max ≈256K

Prompt~224 t/sEstimated

Generate~19.5 t/sEstimated

First token · 4K prompt~18 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 12.0 GiB usable (75% of 16 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 prefill rate per GPU core of 11 measured M2 points (MLX) × this chip's GPU cores ÷ (2 × active params).
Generate estimated from MLX median efficiency 0.8231 (n=60) × memory bandwidth ÷ 3.9 GiB read per token.
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

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 12.0 GiB+8K ctx · max ≈25K

Prompt~98.7 t/sEstimated

Generate~7.9 t/sEstimated

First token · 4K prompt~42 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 12.0 GiB usable (75% of 16 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈25K tokens (native 256K).

Other MLX files

MLX 4-bit 5.5 GiB · fits · files

Where the speeds come from

Prompt estimated from median prefill rate per GPU core of 11 measured M2 points (MLX) × this chip's GPU cores ÷ (2 × active params).
Generate estimated from MLX median efficiency 0.8231 (n=60) × memory bandwidth ÷ 9.7 GiB read per token.
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 12.0 GiB8K ctx · max ≈128K

Prompt—Unknown

Generate~71.8 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 12.0 GiB usable (75% of 16 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 MLX median efficiency 0.8231 (n=60) × memory bandwidth ÷ 1.1 GiB read per token.
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 12.0 GiB+8K ctx · max ≈52K

Prompt~98.7 t/sEstimated

Generate~8.7 t/sEstimated

First token · 4K prompt~42 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 12.0 GiB usable (75% of 16 GB) · 0.5 GiB spare margin required

Max context in free memory: ≈52K tokens (native 256K).

Other MLX files

MLX 4-bit 4.7 GiB · fits · files

Where the speeds come from

Prompt estimated from median prefill rate per GPU core of 11 measured M2 points (MLX) × this chip's GPU cores ÷ (2 × active params).
Generate estimated from MLX median efficiency 0.8231 (n=60) × memory bandwidth ÷ 8.9 GiB read per token.
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 12.0 GiB+8K ctx · max ≈256K

Prompt~1,110 t/sEstimated

Generate~82.2 t/sEstimated

First token · 4K prompt~3.7 sEstimated

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 12.0 GiB usable (75% of 16 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 prefill rate per GPU core of 11 measured M2 points (MLX) × this chip's GPU cores ÷ (2 × active params).
Generate estimated from MLX median efficiency 0.8231 (n=60) × memory bandwidth ÷ 0.9 GiB read per token.
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 12.0 GiB+8K ctx · max ≈256K

Prompt~444 t/sEstimated

Generate~30.9 t/sEstimated

First token · 4K prompt~9.2 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 12.0 GiB usable (75% of 16 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 prefill rate per GPU core of 11 measured M2 points (MLX) × this chip's GPU cores ÷ (2 × active params).
Generate estimated from MLX median efficiency 0.8231 (n=60) × memory bandwidth ÷ 2.5 GiB read per token.
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 4

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

Gemma 4 12B (it)

google/gemma-4-12B-it

2026-06-0312B dense

AA index14.2 AA estimaterank #44

Arena—

Best file & memory

MLX 4-bit6.3 GiB fileCache unknown

7.3 of 12.0 GiB+8K ctx

Prompt~74.3 t/sEstimated

Generate~12.2 t/sEstimated

First token · 4K prompt~55 sEstimated

Memory budget

Weights file	6.28 GiB	mlx-community/gemma-4-12B-it-4bit · 2 files HF files
KV cache · 8K	—	Unknown
Runtime allowance	1.00 GiB	planning assumption Estimated
Recurrent state	—	Unknown
Accounted	7.28 GiB	of 12.0 GiB usable (75% of 16 GB) · 0.5 GiB spare margin required

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

Other MLX files

MLX 8-bit 11.8 GiB · too big · files

Where the speeds come from

Prompt estimated from median prefill rate per GPU core of 11 measured M2 points (MLX) × this chip's GPU cores ÷ (2 × active params).
Generate estimated from MLX median efficiency 0.8231 (n=60) × memory bandwidth ÷ 6.3 GiB read per token.
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

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 12.0 GiB+8K ctx

Prompt~422 t/sEstimated

Generate~46.7 t/sEstimated

First token · 4K prompt~9.7 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 12.0 GiB usable (75% of 16 GB) · 0.5 GiB spare margin required

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

Where the speeds come from

Prompt estimated from median prefill rate per GPU core of 21 measured M2 points (MLX) × this chip's GPU cores ÷ (2 × active params).
Generate estimated from MLX median efficiency 0.3416 (n=94) × memory bandwidth ÷ 0.7 GiB read per token.
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

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 12.0 GiB+8K ctx

Prompt~111 t/sEstimated

Generate~9.3 t/sEstimated

First token · 4K prompt~37 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 12.0 GiB usable (75% of 16 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 prefill rate per GPU core of 11 measured M2 points (MLX) × this chip's GPU cores ÷ (2 × active params).
Generate estimated from MLX median efficiency 0.8231 (n=60) × memory bandwidth ÷ 8.3 GiB read per token.
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 12.0 GiB+8K ctx

Prompt~174 t/sEstimated

Generate~14 t/sEstimated

First token · 4K prompt~24 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 12.0 GiB usable (75% of 16 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 prefill rate per GPU core of 11 measured M2 points (MLX) × this chip's GPU cores ÷ (2 × active params).
Generate estimated from MLX median efficiency 0.8231 (n=60) × memory bandwidth ÷ 5.5 GiB read per token.
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

48 models too big for M2 10c GPU · 16 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)
Qwen3.8-27BMLX 4-bit needs 17.0 GiB
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
K2-Horizon-MoVA-36B-A4BMLX 4-bit needs 26.1 GiB+ (KV unknown)
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
G9v3-39A5B (preview)MLX 4-bit needs 23.0 GiB
Qwen3.5-397B-A17BMLX 4-bit needs 210 GiB
NVIDIA Nemotron 3.5 Bolt 74B-A9BMLX 4-bit needs 41.8 GiB
Qwen3.6-35B-A3BMLX 4-bit needs 20.7 GiB
Qwen3.5-122B-A10BMLX 4-bit needs 66.5 GiB
Muse Glimmer 30BMLX 4-bit needs 19.8 GiB
Gemma 4 26B A4B (it)MLX 4-bit needs 15.8 GiB+ (KV unknown)
Gemma 4 31B (it)MLX 4-bit needs 18.6 GiB+ (KV unknown)
Mistral Medium 3.5 (128B dense)MLX 4-bit needs 76.9 GiB
NVIDIA Nemotron 3.5 Lightning 30B-A3BMLX 4-bit needs 18.1 GiB
IBM Granite 4.2 30BMLX 4-bit needs 18.8 GiB
Nemotron Cascade 2 30B A3BMLX 4-bit needs 18.1 GiB
LongCat-Flash-LiteMLX 4-bit needs 37.4 GiB+ (KV unknown)
Trinity-Large-ThinkingMLX 4-bit needs 212 GiB
Nemotron 3 Nano Omni 30B A3B ReasoningMLX 4-bit needs 19.8 GiB+ (KV unknown)
North Mini CodeMLX 4-bit needs 19.2 GiB
DiffusionGemma 26B A4BMLX 4-bit needs 16.9 GiB+ (KV unknown)
Qwen3-Coder-NextMLX 4-bit needs 43.5 GiB
LFM2.5-24B-A2BMLX 4-bit needs 14.3 GiB
MiniCPM-V 4.7 35B-A3BMLX 4-bit needs 23.6 GiB
Aleph Alpha Kolibri-1MLX 4-bit needs 43.0 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)
Qwen3.6-27BMLX 4-bit needs 17.0 GiB
Kimi K2.6MLX 4-bit needs 614 GiB+ (KV unknown)
NVIDIA Nemotron 3 Super 120B-A12BMLX 4-bit needs 64.9 GiB
Qwen3.5-27BMLX 4-bit needs 17.0 GiB
Qwen3.5-35B-A3BMLX 4-bit needs 20.6 GiB
GLM-4.7-FlashMLX 4-bit needs 17.2 GiB+ (KV unknown)
MiniMax-M2.7MLX 4-bit needs 123 GiB

Specs & sources

Memory	16 GB unified	source
Bandwidth	100 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 Air (M2, 2022)

Measured speeds

5 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.