Apple · M2 · Mini PC

Best AI Models for Mac Mini M2 (16 GB)

Runs 9B models at 11 tok/s; 14B only just fits in 12.5 GB, and 27–31B doesn't fit.

16 GB unified12.5 GB for models100 GB/s7 TFLOPS FP162023

Memory

Same chip in

Mac MiniMacBook Air 13"MacBook Air 15"MacBook Pro 13"

Top models by task

#	Model	Speed	Quant · Memory
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB	11.0 tok/s	Q4_K_M · 6.6 GB
2	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB	24.6 tok/s	Q4_K_M · 5.0 GB
3	Llama 3.2 1B InstructMeta Q4_K_M · 2.3 GB	85.4 tok/s	Q4_K_M · 2.3 GB
4	Gemma 3 1B ITGoogle Q4_K_M · 2.1 GB	106 tok/s	Q4_K_M · 2.1 GB
5	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB	21.5 tok/s	Q4_K_M · 3.4 GB

#	Model	Speed	Reasoning Score	Quant · Memory
1	Gemma 3 4B ITGoogleHow to run → Q4_K_M · 5.0 GB	24.6 tok/s		Q4_K_M · 5.0 GB
2	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB	11.0 tok/s		Q4_K_M · 6.6 GB
3	Llama 3.2 1B InstructMeta Q4_K_M · 2.3 GB	85.4 tok/s	overall	Q4_K_M · 2.3 GB
4	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB	21.5 tok/s		Q4_K_M · 3.4 GB
5	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB	55.1 tok/s		Q4_K_M · 5.5 GB

#	Model	Speed	Quant · Memory
1	Llama 3.2 1B InstructMetaHow to run → Q4_K_M · 2.3 GB	85.4 tok/s	Q4_K_M · 2.3 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB	21.5 tok/s	Q4_K_M · 3.4 GB
3	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB	55.1 tok/s	Q4_K_M · 5.5 GB
4	Gemma 4 E2B ITGoogle Q4_K_M · 3.5 GB	20.4 tok/s	Q4_K_M · 3.5 GB
5	LFM2.5 8B A1BLiquid AI Q4_K_M · 5.6 GB	49.1 tok/s	Q4_K_M · 5.6 GB

#	Model	Speed	Quant · Memory
1	Gemma 3 4B ITGoogleHow to run → Q4_K_M · 5.0 GB	24.6 tok/s	Q4_K_M · 5.0 GB
2	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB	11.0 tok/s	Q4_K_M · 6.6 GB
3	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB	21.5 tok/s	Q4_K_M · 3.4 GB
4	Cosmos Reason2 2BNVIDIA Q4_K_M · 3.5 GB	43.5 tok/s	Q4_K_M · 3.5 GB
5	LocateAnything 3BNVIDIA Q4_K_M · 3.2 GB	26.2 tok/s	Q4_K_M · 3.2 GB

See all 257 models on the Mac Mini M2 →Bars = traction for models without a Score yet
Task rankings use that task's benchmarks, topped up from Overall when short; bars mark well-known models with no Score yet.

About the Mac Mini M2 (16 GB)

The Mac Mini M2 is a 16 GB mini PC with more memory than speed: it runs 9B models at 11 tok/s. macOS keeps about 3.5 GB, leaving 12.5 GB for models. Prompt reading is its weak spot: a 4K-token prompt waits 55 s before the first word on Qwen3.5 9B. M2 generation, released 2023; the newer M3 writes 2% faster with 1.0× the compute.

Speed in 16 GB#7100 GB/s

Prompt reading#67 TFLOPS

For models12.5 GBmacOS keeps 3.5 GB

ChipM2released 2023

Mac Mini M2 strengths and weaknesses

Weaknesses

27–31B models don't fit: Qwen3.8 27B needs 17.9 GB at Q4 vs 12.5 GB usable here
Little room for context: Qwen3 14B uses 11.9 of 12.5 GB usable, 0.6 GB left
Slow prompt reading: A 32K-token prompt on Qwen3.5 9B waits 7.4 min for the first token
No CUDA: vLLM, AWQ, GPTQ and FP8 builds don't run; use GGUF or MLX

Memory for models

12.5 GB of 16 GB

9B6.6 GB14B11.9 GB

For models 12.5 GBmacOS keeps 3.5 GBModel size at Q4

27–31B models need 17.9 GB at Q4, more than the 12.5 GB available. The 24 GB config fits Qwen3.8 27B →

Similar devices and alternatives

Other memory sizes of the same machine first, then machines and GPUs people weigh against it, each with the one reason it is worth a look. Speeds on Qwen3.6 35B A3B.

Same chip, 8 GB more memoryMac Mini M2 (24 GB)Apple · 20.5 GB for models · M2

▼ 34% speed▲ 8 GBno price

Same family 14% faster, same memoryMac Mini M4 (16 GB)Apple · 12.5 GB for models · M4

▲ 14% speedsame memory$799

39% faster, 8 GB more memoryMac Mini M4 Pro (24 GB)Apple · 20.5 GB for models · M4 Pro

▲ 39% speed▲ 8 GB$1,599

Reads prompts 4× faster, 32.5 GB for modelsMac Studio M4 Max (36 GB)Apple · 32.5 GB for models · M4 Max

▲ 4× prompts▲ 65% speed▲ 20 GB$2,499

Reads prompts 52× faster, 24 GB for modelsRTX 4090NVIDIA · 24 GB VRAM · GPU

▲ 52× prompts▲ 352% speed▲ 11.5 GB$1,599rent $0.34/hr

Reads prompts 66× faster, 32 GB for modelsRTX 5090NVIDIA · 32 GB VRAM · GPU

▲ 66× prompts▲ 539% speed▲ 19.5 GB$5,376rent $0.69/hr

Mac Mini M2 tokens per second by model size

Output speed depends on memory bandwidth (100 GB/s). Grey rows need more than the 12.5 GB available.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
11.0tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB tight · Q4_K_M
7.4tok/s
27–31BQwen3.8 27B · does not fit
needs 17.9 GB
35B MoEQwen3.6 35B A3B · does not fit
needs 22.0 GB
70BLlama 3.3 70B Instruct · does not fit
needs 51.3 GB
120B MoEGPT OSS 120B · does not fit
needs 70.8 GB

Estimated speeds: Q4_K_M, 4K context, one user. How we estimate

Chip generations: writing vs compute

M1 → M4

Writing speed (tok/s)Compute (TFLOPS FP16)

Writing speed follows memory bandwidth and barely moved: 24.9 to 38.1 tok/s since the M1. Compute, which sets how fast prompts are read, grew 1.7×. Indexed to the M1; speeds on Qwen3.6 35B A3B, same 16 GB.

All 257 models on the Mac Mini M2

Featured only

Best quant that fits in 12.5 GB, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works

LLM models compatible with Mac Mini M2 (16 GB) — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Qwen3.5 9B9.7BVisionFunctions 9.7B·Q4_K_M·11.0 t/s·262K ctx	Q4_K_M	6.6 GB53%	11.0 t/s	262K	B49, Decent
Qwen3.8 27B27.8BVisionFunctions 27.8B·IQ3_XXS·6.1 t/s·262K ctx	IQ3_XXS	12.0 GB96%	6.1 t/s	262K	D18, Barely runs
Gemma 4 12B IT12.0BChatFunctions 12.0B·Q4_K_M·8.5 t/s·262K ctx	Q4_K_M	9.0 GB72%	8.5 t/s	262K	B46, Decent
Qwen3.5 4B4.7BVisionFunctions 4.7B·Q4_K_M·21.5 t/s·262K ctx	Q4_K_M	3.4 GB27%	21.5 t/s	262K	B62, Decent
Gemma 4 E4B IT8.0BChatFunctions 8.0B·Q4_K_M·13.2 t/s·131K ctx	Q4_K_M	5.6 GB44%	13.2 t/s	131K	B52, Decent
Ling 3.0 Tiny7.9BChatFunctions 7.9B·Q4_K_M·55.1 t/s·131K ctx	Q4_K_M	5.5 GB44%	55.1 t/s	131K	A82, Runs well
Gemma 4 E2B IT5.1BChatFunctions 5.1B·Q4_K_M·20.4 t/s·131K ctx	Q4_K_M	3.5 GB28%	20.4 t/s	131K	B60, Decent
LFM2.5 8B A1B8.5BChatFunctions 8.5B·Q4_K_M·49.1 t/s·128K ctx	Q4_K_M	5.6 GB45%	49.1 t/s	128K	A79, Runs well
MiniCPM5 2B2.5BChatFunctions 2.5B·Q4_K_M·36.8 t/s·131K ctx	Q4_K_M	2.5 GB20%	36.8 t/s	131K	A74, Runs well
Qwen3.5 2B2.3BVisionFunctions 2.3B·Q4_K_M·39.5 t/s·262K ctx	Q4_K_M	1.9 GB15%	39.5 t/s	262K	A75, Runs well
Gemma 4 26B A4B IT25.8BVisionFunctions 25.8B·Q3_K_S·28.5 t/s·262K ctx	Q3_K_S	12.3 GB98%	28.5 t/s	262K	C41, Usable
Ornith 1.0 9B9.4BChatFunctions 9.4B·Q4_K_M·11.3 t/s·262K ctx	Q4_K_M	6.5 GB52%	11.3 t/s	262K	B50, Decent
MiMo V2.6 Distill Qwen 9B9.4BVisionCodeFunctions 9.4B·Q4_K_M·11.3 t/s·262K ctx	Q4_K_M	6.5 GB52%	11.3 t/s	262K	B50, Decent
ZAYA1 VL 8B9.7BVision 9.7B·Q4_K_M·69.1 t/s·33K ctx	Q4_K_M	7.5 GB60%	69.1 t/s	33K	S86, Runs great
Apertus V1.5 8B8.9BVision 8.9B·Q4_K_M·11.9 t/s	Q4_K_M	8.5 GB68%	11.9 t/s	—	B51, Decent

Mac Mini M2 specs

Specs

Chip: M2
CPU cores: 8
GPU cores: 10
Unified memory: 16 GB
For models: 12.5 GB (macOS keeps 3.5 GB)
Memory bandwidth: 100 GB/s
FP16 (dense): 7.2 TFLOPS
Neural Engine: 16 TOPS
Released: 2023-01-24

Mac Mini M2 FAQ

How much memory is available for AI on the Mac Mini M2 (16 GB)?

About 12.5 GB of the 16 GB. macOS keeps roughly 3.5 GB for itself and other apps.

What is the largest model the Mac Mini M2 (16 GB) can run?

GPT OSS 20B (20.9B) at Q4_K_S uses 12.4 GB, 99% of the available memory, and runs at about 25.3 tok/s.

Can the Mac Mini M2 (16 GB) run 27–31B models?

No. Qwen3.8 27B needs 17.9 GB at Q4, more than the 12.5 GB available.

How long does the Mac Mini M2 (16 GB) take to read a long prompt?

On Qwen3.5 9B, about 55 s for a 4K-token prompt and 7.4 min for a 32K-token document before the first word appears.

Is renting a GPU cheaper than buying the Mac Mini M2?

A Tesla V100 (16 GB) rents from $0.08/hr.

12 GB GPUs All Macs Desktops & mini PCs Mac Mini M2 Pro MacBook Pro 14" M1 Pro MacBook Pro 14" M2 Pro MacBook Pro 16" M1 Pro MacBook Pro 16" M2 Pro MacBook Air 13" M5 Best coding LLMs All hardware