Apple · M1 · Mini PC

Best AI Models for Mac Mini M1 (16 GB)

Runs 9B models at 8 tok/s; 14B only just fits in 12.5 GB, and 27–31B doesn't fit.

16 GB unified12.5 GB for models68.3 GB/s5 TFLOPS FP162020

Memory

Same chip in

Mac MiniiMac 24"MacBook Air 13"MacBook Pro 13"

Top models by task

#	Model	Speed	Quant · Memory
1	Gemma 3 4B ITGoogleHow to run → Q4_K_M · 5.0 GB	16.8 tok/s	Q4_K_M · 5.0 GB
2	Llama 3.2 1B InstructMeta Q4_K_M · 2.3 GB	58.3 tok/s	Q4_K_M · 2.3 GB
3	Gemma 3 1B ITGoogle Q4_K_M · 2.1 GB	72.4 tok/s	Q4_K_M · 2.1 GB
4	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB	41.1 tok/s	Q4_K_M · 5.5 GB
5	LFM2.5 8B A1BLiquid AI Q4_K_M · 5.6 GB	36.2 tok/s	Q4_K_M · 5.6 GB

#	Model	Speed	Quant · Memory
1	Llama 3.2 1B InstructMetaHow to run → Q4_K_M · 2.3 GB	58.3 tok/s	Q4_K_M · 2.3 GB
2	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB	41.1 tok/s	Q4_K_M · 5.5 GB
3	LFM2.5 8B A1BLiquid AI Q4_K_M · 5.6 GB	36.2 tok/s	Q4_K_M · 5.6 GB
4	Qwen3.5 2BAlibaba Q4_K_M · 1.9 GB	27.0 tok/s	Q4_K_M · 1.9 GB
5	MiniCPM5 2BOpenBMB Q4_K_M · 2.5 GB	25.2 tok/s	Q4_K_M · 2.5 GB

#	Model	Speed	Quant · Memory
1	Gemma 3 4B ITGoogleHow to run → Q4_K_M · 5.0 GB	16.8 tok/s	Q4_K_M · 5.0 GB
2	Qwen3.5 2BAlibaba Q4_K_M · 1.9 GB	27.0 tok/s	Q4_K_M · 1.9 GB
3	Cosmos Reason2 2BNVIDIA Q4_K_M · 3.5 GB	29.7 tok/s	Q4_K_M · 3.5 GB
4	LocateAnything 3BNVIDIA Q4_K_M · 3.2 GB	17.9 tok/s	Q4_K_M · 3.2 GB
5	Qwen3.5 0.8BAlibaba Q4_K_M · 0.9 GB	55.0 tok/s	Q4_K_M · 0.9 GB

See all 257 models on the Mac Mini M1 →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 M1 (16 GB)

The Mac Mini M1 is a 16 GB mini PC with more memory than speed: it runs 9B models at 8 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 34 s before the first word on Gemma 3 4B IT. M1 generation, released 2020; the newer M2 writes 34% faster with 1.4× the compute.

Speed in 16 GB#868 GB/s

Prompt reading#85 TFLOPS

For models12.5 GBmacOS keeps 3.5 GB

ChipM1released 2020

Mac Mini M1 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 Gemma 3 4B IT waits 4.5 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.

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.

53% faster, same memoryMac Mini M4 (16 GB)Apple · 12.5 GB for models · M4

▲ 53% speedsame memory$799

Reads prompts 3× faster, 20.5 GB for modelsMac Mini M4 Pro (24 GB)Apple · 20.5 GB for models · M4 Pro

▲ 3× prompts▲ 86% speed▲ 8 GB$1,599

Reads prompts 3× faster, 24 GB for modelsMacBook Pro 14 M5Apple · 24 GB for models · M5

▲ 3× prompts▲ 15% speed▲ 11.5 GB$1,839

Reads prompts 5× faster, 32.5 GB for modelsMac Studio M4 Max (36 GB)Apple · 32.5 GB for models · M4 Max

▲ 5× prompts▲ 122% speed▲ 20 GB$2,499

Reads prompts 72× faster, 24 GB for modelsRTX 4090NVIDIA · 24 GB VRAM · GPU

▲ 72× prompts▲ 506% speed▲ 11.5 GB$1,599rent $0.34/hr

Reads prompts 91× faster, 32 GB for modelsRTX 5090NVIDIA · 32 GB VRAM · GPU

▲ 91× prompts▲ 757% speed▲ 19.5 GB$5,376rent $0.69/hr

Mac Mini M1 tokens per second by model size

Output speed depends on memory bandwidth (68 GB/s). Grey rows need more than the 12.5 GB available.

9BQwen3.5 9B · Q4_K_M · 6.6 GB slow
7.5tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB tight · Q4_K_M
5.0tok/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 M1

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 M1 (16 GB) — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Qwen3.5 9B9.7BVisionFunctions 9.7B·Q4_K_M·7.5 t/s·262K ctx	Q4_K_M	6.6 GB53%	7.5 t/s	262K	B45, Decent
Qwen3.8 27B27.8BVisionFunctions 27.8B·IQ3_XXS·4.2 t/s·262K ctx	IQ3_XXS	12.0 GB96%	4.2 t/s	262K	D16, Barely runs
Gemma 4 12B IT12.0BChatFunctions 12.0B·Q4_K_M·5.8 t/s·262K ctx	Q4_K_M	9.0 GB72%	5.8 t/s	262K	C43, Usable
Qwen3.5 4B4.7BVisionFunctions 4.7B·Q4_K_M·14.7 t/s·262K ctx	Q4_K_M	3.4 GB27%	14.7 t/s	262K	B54, Decent
Gemma 4 E4B IT8.0BChatFunctions 8.0B·Q4_K_M·9.0 t/s·131K ctx	Q4_K_M	5.6 GB44%	9.0 t/s	131K	B47, Decent
Ling 3.0 Tiny7.9BChatFunctions 7.9B·Q4_K_M·41.1 t/s·131K ctx	Q4_K_M	5.5 GB44%	41.1 t/s	131K	A75, Runs well
Gemma 4 E2B IT5.1BChatFunctions 5.1B·Q4_K_M·13.9 t/s·131K ctx	Q4_K_M	3.5 GB28%	13.9 t/s	131K	B53, Decent
LFM2.5 8B A1B8.5BChatFunctions 8.5B·Q4_K_M·36.2 t/s·128K ctx	Q4_K_M	5.6 GB45%	36.2 t/s	128K	A73, Runs well
Qwen3.5 2B2.3BVisionFunctions 2.3B·Q4_K_M·27.0 t/s·262K ctx	Q4_K_M	1.9 GB15%	27.0 t/s	262K	A68, Runs well
MiniCPM5 2B2.5BChatFunctions 2.5B·Q4_K_M·25.2 t/s·131K ctx	Q4_K_M	2.5 GB20%	25.2 t/s	131K	A66, Runs well
ZAYA1 VL 8B9.7BVision 9.7B·Q4_K_M·57.2 t/s·33K ctx	Q4_K_M	7.5 GB60%	57.2 t/s	33K	A82, Runs well
Ornith 1.0 9B9.4BChatFunctions 9.4B·Q4_K_M·7.7 t/s·262K ctx	Q4_K_M	6.5 GB52%	7.7 t/s	262K	B45, Decent
MiMo V2.6 Distill Qwen 9B9.4BVisionCodeFunctions 9.4B·Q4_K_M·7.7 t/s·262K ctx	Q4_K_M	6.5 GB52%	7.7 t/s	262K	B45, Decent
Gemma 4 26B A4B IT25.8BVisionFunctions 25.8B·Q3_K_S·20.6 t/s·262K ctx	Q3_K_S	12.3 GB98%	20.6 t/s	262K	C32, Usable
Apertus V1.5 8B8.9BVision 8.9B·Q4_K_M·8.1 t/s	Q4_K_M	8.5 GB68%	8.1 t/s	—	B45, Decent

Mac Mini M1 specs

Specs

Chip: M1
CPU cores: 8
GPU cores: 8
Unified memory: 16 GB
For models: 12.5 GB (macOS keeps 3.5 GB)
Memory bandwidth: 68.3 GB/s
FP16 (dense): 5.2 TFLOPS
Neural Engine: 11 TOPS
Released: 2020-11-17

Mac Mini M1 FAQ

How much memory is available for AI on the Mac Mini M1 (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 M1 (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 18.0 tok/s.

Can the Mac Mini M1 (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 M1 (16 GB) take to read a long prompt?

On Gemma 3 4B IT, about 34 s for a 4K-token prompt and 4.5 min for a 32K-token document before the first word appears.

Is renting a GPU cheaper than buying the Mac Mini M1?

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 Mac Mini M2 Best coding LLMs All hardware