LocalFit
Submit a benchmark

Apple M6 Mac mini12CPU/12GPU 16GB: what runs best?

RTX 4090RTX 5090RTX 3090RTX 4060 Ti (16 GB)RTX 5070 TiRadeon RX 7900 XTXM4 Max 128 GBM3 Ultra 512 GBDGX Spark (128 GB)All devices

Apple · Apple Silicon Mac

Apple M6 Mac mini12CPU/12GPU 16GB

Memory16 GB unifiedBandwidth153 GB/s vendor specPlanned for models75% of unified memory (editable)

Unified memory

Context
KV cache
Mode
Advanced: reserves, bandwidth, workload, models

Defaults are editorial planning choices, not measurements: 1 GiB runtime + 0.5 GiB margin per device, 75% of unified memory, 8 GiB RAM for the OS, a vendor “24 GB” treated as 24 GiB (enter your driver’s available VRAM to override), 5 t/s minimum speed (research editorial default). Memory ledger

Apple M6 Mac mini12CPU/12GPU 16GB · 75% (12.0 GiB) planned for models · 153 GB/s8K contextF16 KVany backend≥ 5 t/s

Best plans Apple M6 Mac mini12CPU/12GPU 16GB

Best quality at ≥ 5 t/s

K2-Horizon-7B

20.6 AA index single mode

Q8_0llama.cpp MetalUnified memory

~8.4–13 t/s Estimated

Faster tradeoff

K2-Horizon-3.7B

15.6 AA index single mode

Q8_0llama.cpp MetalUnified memory

~14–22 t/s Estimated

Next point on the quality/speed front; then Qwen3.5-4B.

Possibly better · speed not established

No higher-scoring model has a feasible plan here.

WeightsKV cacheReserveFreeFits* = a state term unsizedMeasuredlinks to its sourceEstimatedcalibrated or extrapolated range, ~Ceilingupper bound, ≤Unknownnever zero

Meets your 5 t/s floor 22

Best plan per model that reaches your floor by a matching measurement, a calibrated range, or an extrapolated estimate (labelled). Sorted by the selected quality metric, then speed.

  1. 1

    K2-Horizon-7B

    IFM/K2-Horizon-7B

    2026-09-039B tensors · dense

    AA index20.6single mode
    Plan & memory
    Q8_0llama.cpp MetalUnified memoryFits
    Unified11.5 / 12.0 GiB
    Generate~8.4–13 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
  2. 2

    K2-Horizon-3.7B

    IFM/K2-Horizon-3.7B

    2026-09-035.1B tensors · dense

    AA index15.6single mode
    Plan & memory
    Q8_0llama.cpp MetalUnified memoryFits
    Unified7.6 / 12.0 GiB
    Generate~14–22 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
  3. 3

    Qwen3.5-4B

    Qwen/Qwen3.5-4B

    2026-03-024B dense

    AA index13.1 est.Reasoning
    Plan & memory
    Q8_0llama.cpp MetalUnified memoryFits*
    Unified6.1 / 12.0 GiB
    Generate~18–28 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
  4. 4

    MiniCPM5-2B

    openbmb/MiniCPM5-2B

    2026-09-072.5B dense

    AA index12.5single mode
    Plan & memory
    FP16llama.cpp MetalUnified memoryFits
    Unified6.5 / 12.0 GiB
    Generate~16–26 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
  5. 5

    Qwen3.5-9B

    Qwen/Qwen3.5-9B

    2026-03-029B dense

    AA index11.2Reasoning
    Plan & memory
    Q8_0llama.cpp MetalUnified memoryFits*
    Unified10.9 / 12.0 GiB
    Generate~8.6–13 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
  6. 6

    granite-4.2-8b

    ibm-granite/granite-4.2-8b

    2026-08-258B dense

    AA index11.1single mode
    Plan & memory
    Q8_0llama.cpp MetalUnified memoryFits
    Unified11.5 / 12.0 GiB
    Generate~8.5–13 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
  7. 7

    G9v3-3B

    ai9stars/G9v3-3B

    2026-07 (day unknown)3B dense

    AA index10.8 est.single mode
    Plan & memory
    FP16llama.cpp MetalUnified memoryFits
    Unified7.5 / 12.0 GiB
    Generate~14–21 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
  8. 8

    granite-4.2-3b

    ibm-granite/granite-4.2-3b

    2026-08-253B dense

    AA index9.1single mode
    Plan & memory
    Q8_0llama.cpp MetalUnified memoryFits
    Unified5.8 / 12.0 GiB
    Generate~20–31 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
  9. 9

    LFM2.5-2.6B

    LiquidAI/LFM2.5-2.6B

    2026-08-042.7B dense

    AA index8.4 est.single mode
    Plan & memory
    FP16llama.cpp MetalUnified memoryFits*
    Unified6.7 / 12.0 GiB
    Generate~16–24 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
  10. 10

    LFM2.5-8B-A1B

    LiquidAI/LFM2.5-8B-A1B

    2026-05-288.3B MoE · 1.5B active

    AA index7.2 est.single mode
    Plan & memory
    MLX 8-bitMLX-LMUnified memoryFits*
    Unified10.0 / 12.0 GiB
    Generate~17–49 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
  11. 11

    Qwen3.5-2B

    Qwen/Qwen3.5-2B

    2026-03-022B dense

    AA index6.9 est.Reasoning
    Plan & memory
    Q8_0llama.cpp MetalUnified memoryFits*
    Unified3.5 / 12.0 GiB
    Generate~40–62 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
  12. 12

    Qwen3.5-0.8B

    Qwen/Qwen3.5-0.8B

    2026-03-020.8B dense

    AA index6.1 est.Reasoning
    Plan & memory
    Q8_0llama.cpp MetalUnified memoryFits*
    Unified2.4 / 12.0 GiB
    Generate~96–150 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
  13. 13

    Phi-4Older

    microsoft/phi-4

    2024-12-1215B tensors · dense

    AA index5.9 est.single mode
    Plan & memory
    Q4_K_Mllama.cpp MetalUnified memoryFits
    Unified11.3 / 12.0 GiB
    Generate~8.8–14 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
  14. 14

    Olmo-3-7B-ThinkSpecialist

    allenai/Olmo-3-7B-Think

    2025-11-207.3B tensors · dense

    AA index5.6 est.single mode
    Plan & memory
    Q8_0llama.cpp MetalUnified memoryFits
    Unified11.2 / 12.0 GiB
    Generate~8.6–13 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
  15. 15

    Olmo-3-7B-Instruct

    allenai/Olmo-3-7B-Instruct

    2025-11-207.3B tensors · dense

    AA index5.2 est.single mode
    Plan & memory
    Q8_0llama.cpp MetalUnified memoryFits
    Unified11.2 / 12.0 GiB
    Generate~8.6–13 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
  16. 16

    LFM2.5-1.2B-ThinkingSpecialist

    LiquidAI/LFM2.5-1.2B-Thinking

    2026-01-201.2B tensors · dense

    AA index5.2 est.single mode
    Plan & memory
    FP16llama.cpp MetalUnified memoryFits*
    Unified3.8 / 12.0 GiB
    Generate~36–56 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
  17. 17

    LFM2.5-1.2B-Instruct

    LiquidAI/LFM2.5-1.2B-Instruct

    2026-01-051.2B tensors · dense

    AA index5.2 est.single mode
    Plan & memory
    FP16llama.cpp MetalUnified memoryFits*
    Unified3.8 / 12.0 GiB
    Generate~36–56 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
  18. 18

    Molmo2-8BSpecialist

    allenai/Molmo2-8B

    2025-12-118.7B tensors · dense

    AA index5.0 est.single mode
    Plan & memory
    Q8_0llama.cpp MetalUnified memoryFits
    Unified10.7 / 12.0 GiB
    Generate~9.2–14 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
  19. 19

    LFM2.5-VL-1.6BSpecialist

    LiquidAI/LFM2.5-VL-1.6B

    2026-01-051.6B tensors · dense

    AA index4.8 est.single mode
    Plan & memory
    FP16llama.cpp MetalUnified memoryFits*
    Unified3.8 / 12.0 GiB
    Generate~36–56 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
  20. 20

    Apertus-8B-Instruct-2509

    swiss-ai/Apertus-8B-Instruct-2509

    2025-09-028.1B tensors · dense

    AA index4.8 est.single mode
    Plan & memory
    Q8_0llama.cpp MetalUnified memoryFits
    Unified10.5 / 12.0 GiB
    Generate~9.4–15 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
  21. 21

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

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

    2026-03-164B dense

    AA index4.8single mode
    Plan & memory
    Q8_0llama.cpp MetalUnified memoryFits*
    Unified5.6 / 12.0 GiB
    Generate~20–31 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
  22. 22

    K2-Horizon-0.9B

    IFM/K2-Horizon-0.9B

    2026-09-031.1B tensors · dense

    AA index3.0single mode
    Plan & memory
    Q8_0llama.cpp MetalUnified memoryFits
    Unified3.0 / 12.0 GiB
    Generate~62–96 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
+ 40 models without a AA index score

Memory not fully resolved 6

The weights fit, but the KV cache for this attention type (or the chosen cache layout) is not established, so a fit cannot be guaranteed.

  1. 1

    gemma-4-12B-it

    google/gemma-4-12B-it

    2026-06-0312B dense

    AA index14.2 est.Reasoning
    Plan & memory
    Q5_K_Mllama.cpp MetalUnified memoryKV unknown
    Unified9.7+ / 12.0 GiB
    Generate~9.7–15 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
  2. 2

    Ling-3.0-tiny

    inclusionAI/Ling-3.0-tiny

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

    AA index11.1single mode
    Plan & memory
    Q8_0llama.cpp MetalUnified memoryKV unknown
    Unified9.3+ / 12.0 GiB
    Generate~21–60 t/sEstimatedextrapolated≈ meets 5 t/s
    First token · 4K prompt—Unknown
  3. 3

    gemma-4-E4B-it

    google/gemma-4-E4B-it

    2026-04-028B dense

    AA index8.9Reasoning
    Plan & memory
    Q8_0llama.cpp MetalUnified memoryKV unknown
    Unified9.0+ / 12.0 GiB
    Generate~11–17 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
  4. 4

    gemma-4-E2B-it

    google/gemma-4-E2B-it

    2026-04-025.1B dense

    AA index7.8 est.Reasoning
    Plan & memory
    Q8_0llama.cpp MetalUnified memoryKV unknown
    Unified6.1+ / 12.0 GiB
    Generate~17–27 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
  5. 5

    Phi-4-mini-instructOlder

    microsoft/Phi-4-mini-instruct

    2025-02-263.8B tensors · dense

    AA index6.3 est.single mode
    Plan & memory
    FP16llama.cpp MetalUnified memoryKV unknown
    Unified8.7+ / 12.0 GiB
    Generate~11–17 t/sEstimatedmeets 5 t/s
    First token · 4K prompt—Unknown
  6. 6

    tiny-aya-globalGated

    CohereLabs/tiny-aya-global

    2026-02-173.3B tensors

    AA index4.8 est.single mode
    Plan & memory
    FP16llama.cpp MetalUnified memoryKV unknown
    Unified7.7+ / 12.0 GiB
    Generate—Unknownspeed unknown
    First token · 4K prompt—Unknown
+ 19 models without a AA index score

Speed unknown 4

No measurement, calibration or bandwidth figure for this plan.

  1. 1

    granite-4.0-h-1b

    ibm-granite/granite-4.0-h-1b

    2025-10-281.5B tensors · MoE

    AA index5.2 est.single mode
    Plan & memory
    Q8_0llama.cpp MetalUnified memoryFits*
    Unified3.0 / 12.0 GiB
    Generate—Unknownspeed unknown
    First token · 4K prompt—Unknown
  2. 2

    granite-4.0-micro

    ibm-granite/granite-4.0-micro

    2025-10-023.4B tensors · MoE

    AA index5.1 est.single mode
    Plan & memory
    Q8_0llama.cpp MetalUnified memoryFits
    Unified5.5 / 12.0 GiB
    Generate—Unknownspeed unknown
    First token · 4K prompt—Unknown
  3. 3

    granite-4.0-350m

    ibm-granite/granite-4.0-350m

    2025-10-280.4B tensors · MoE

    AA index4.8 est.single mode
    Plan & memory
    Q8_0llama.cpp MetalUnified memoryFits
    Unified2.1 / 12.0 GiB
    Generate—Unknownspeed unknown
    First token · 4K prompt—Unknown
  4. 4

    granite-4.0-h-350m

    ibm-granite/granite-4.0-h-350m

    2025-10-280.3B tensors · MoE

    AA index4.8 est.single mode
    Plan & memory
    Q8_0llama.cpp MetalUnified memoryFits*
    Unified1.9 / 12.0 GiB
    Generate—Unknownspeed unknown
    First token · 4K prompt—Unknown
+ 2 models without a AA index score
144 models with no feasible plan on this setup

Specs & sources

Memory16 GB unifiedsource
Bandwidth153 GB/ssource
FP16unknownNo unambiguous comparable value verified; never substitute AI TOPS, BF16, or whole-system power.
PowerunknownNo unambiguous comparable value verified; never substitute AI TOPS, BF16, or whole-system power.
  • Support page lists 153/170GB/s and assigns 170GB/s to 24GB/32GB configurable memory.16GB therefore retains 153GB/s; do not give every M6 memory bin 170GB/s. GPU FP16 and GPU-only TDP not published.

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.