Apple · M6 · Mini PC

Best AI Models for Mac Mini M6 (32 GB)

Runs 9B and 35B MoE models well; 14B and 27–31B fit but are slow (13 and 7 tok/s), and 70B doesn't fit in 28.5 GB.

32 GB unified28.5 GB for models170 GB/s19 TFLOPS FP162026

Buy$1,299

Memory

16 GB$899 24 GB$1,099 32 GB$1,299

Same chip in

Mac Mini$1,299 MacBook Pro 14"$2,399 iMac 24"$2,099

What LLMs can the Mac Mini M6 run?

#	Model	Speed	Quant · Memory
1	Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB · 30.9 t/s	30.9 tok/s	Q4_K_M · 22.0 GB
2	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 34.4 t/s	34.4 tok/s	Q4_K_M · 16.5 GB
3	Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 37.2 t/s	37.2 tok/s	Q4_K_M · 19.4 GB
4	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 37.6 t/s	37.6 tok/s	Q4_K_M · 13.1 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 44.4 t/s	44.4 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · Memory
1	Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB · 30.9 t/s	30.9 tok/s	Q4_K_M · 22.0 GB
2	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 34.4 t/s	34.4 tok/s	Q4_K_M · 16.5 GB
3	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 37.6 t/s	37.6 tok/s	Q4_K_M · 13.1 GB
4	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 22.5 t/s	22.5 tok/s	Q4_K_M · 7.9 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 44.4 t/s	44.4 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · Memory
1	Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB · 30.9 t/s	30.9 tok/s	Q4_K_M · 22.0 GB
2	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 34.4 t/s	34.4 tok/s	Q4_K_M · 16.5 GB
3	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 18.7 t/s	18.7 tok/s	Q4_K_M · 6.6 GB
4	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 37.6 t/s	37.6 tok/s	Q4_K_M · 13.1 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 44.4 t/s	44.4 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · Memory
1	Gemma 4 26B A4B ITGoogleHow to run → Q4_K_M · 16.5 GB · 34.4 t/s	34.4 tok/s	Q4_K_M · 16.5 GB
2	Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 37.2 t/s	37.2 tok/s	Q4_K_M · 19.4 GB
3	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 18.7 t/s	18.7 tok/s	Q4_K_M · 6.6 GB
4	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 37.6 t/s	37.6 tok/s	Q4_K_M · 13.1 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 44.4 t/s	44.4 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed ↓	Quant · Memory
1	GPT OSS 20BOpenAIHow to run → Q4_K_M · 13.1 GB · 37.6 t/s	37.6 tok/s	Q4_K_M · 13.1 GB
2	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 44.4 t/s	44.4 tok/s	Q4_K_M · 19.3 GB
3	Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 37.2 t/s	37.2 tok/s	Q4_K_M · 19.4 GB
4	Qwen3 30B A3B Instruct 2507Alibaba Q4_K_M · 19.4 GB · 37.2 t/s	37.2 tok/s	Q4_K_M · 19.4 GB
5	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 34.4 t/s	34.4 tok/s	Q4_K_M · 16.5 GB

See all 343 models on the Mac Mini M6 →Bars = traction for models without a Score yet

About the Mac Mini M6 (32 GB)

The Mac Mini M6 is a mid-range 32 GB mini PC: it runs 9B and 35B MoE models well. macOS keeps about 3.5 GB, leaving 28.5 GB for models. Prompt reading is its weak spot: a 4K-token prompt waits 10 s before the first word on Qwen3.6 35B A3B. At its $1,299 MSRP it gives 14.4 tok/s per $1,000, 5th of the 6 machines compared here.

Speed in 32 GB#7170 GB/s

Prompt reading#819 TFLOPS

For models28.5 GBmacOS keeps 3.5 GB

ChipM6released 2026

Mac Mini M6 strengths and weaknesses

Strengths

Runs 35B MoE models: Qwen3.6 35B A3B at 30.9 tok/s in 22 GB

Weaknesses

70B models don't fit: Llama 3.3 70B Instruct needs 51.3 GB at Q4 vs 28.5 GB usable here
Slow on large dense models: Qwen3.8 27B at 6.8 tok/s
Slow prompt reading: A 32K-token prompt on Qwen3.6 35B A3B waits 1.4 min for the first token
No CUDA: vLLM, AWQ, GPTQ and FP8 builds don't run; use GGUF or MLX

Memory for models

28.5 GB of 32 GB

9B6.6 GB14B11.9 GB27–31B17.9 GB35B MoE22 GB

9B6.6 GB14B11.9 GB35B MoE22 GB

For models 28.5 GBmacOS keeps 3.5 GBModel size at Q4

70B models need 51.3 GB at Q4, more than the 28.5 GB available.Or rent an A100 (80 GB) from $1.15/hr →

Speed per dollar and per watt

NewUsed

On Qwen3.5 9B (9B params) at Q4_K_M. New means a shop price, either a street quote or the maker's own price; used is compared with used. The last two columns are the speed you get per $1,000 of price and per 100 W of power; higher is better. The Mac Mini M6 has no current new price, so it is shown at its MSRP.

Machine	New price	tok/s	tok/s per $1,000	tok/s per 100 W
RTX 509032 GB	about $5,502	183	33.3	31.8
Mac Mini M616 GB	about $899	16.9	18.8	–
Mac Studio M4 Max36 GB	about $2,499	45.1	18.0	31.1
Mac Mini M624 GB	about $1,099	18.7	17.0	–
Mac Mini M632 GB	about $1,299	18.7	14.4	–
Mac Mini M432 GB	about $999	13.2	13.2	20.3

Machine	Used price	tok/s	tok/s per $1,000	tok/s per 100 W
RTX 409024 GBBest used value	about $3,000	103	34.3	22.9
RTX 509032 GB	about $7,000	183	26.2	31.8
Mac Studio M4 Max36 GB	about $2,000	45.1	22.6	31.1

Cost per token: the Mac Mini M6 against 16–36 GB machines and GPUs

On Qwen3.5 9B (9B params, Q4_K_M, 4K context). Speed, cost per token and power per token depend on the model.

NewUsed

Speed$ per 1M tokens

≤16 GB24–36 GBthis mini PCat MSRP

Cost per 1M output tokenson Qwen3.5 9B · card over 3 years + power

$4.41

Machine, MSRP: $4.41
Power: not published

3-year cost of ownership$1,299

Or rent an A100 in the cloud$0.58/hr

Renting costs as much as buying after ≈2,200 hours (≈1.5 years at 4 h a day).

Power$/kWhUseh/dayKeepyears

Each dot is a machine or GPU; hover or tap it for its numbers, click to open it. Machines without a price for the chosen basis are left out. Machines without a published power figure are left out of Per watt and costed without power. How we calculate cost per token

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 Qwen3.5 9B.

Same chip, 8 GB less memory for $200 lessMac Mini M6 (24 GB)Apple · 20.5 GB for models · M6

same speed▼ $200 less▼ 8 GB$1,099

Same family Same chip, 16 GB less memory for $400 lessMac Mini M6 (16 GB)Apple · 12.5 GB for models · M6

▼ 10% speed▼ $400 less▼ 16 GB$899

Same family Machine, 29% slowerMac Mini M4 (32 GB)Apple · 28.5 GB for models · M4

▼ 29% speedsame memory$999

141% faster, 4 GB more memoryMac Studio M4 Max (36 GB)Apple · 32.5 GB for models · M4 Max

▲ 141% speed▲ 4 GB$2,499

Reads prompts 19× faster, 24 GB for modelsRTX 4090NVIDIA · 24 GB VRAM · GPU

▲ 19× prompts▲ 451% speed▼ 4.5 GB$1,599rent $0.34/hr

Reads prompts 25× faster, 32 GB for modelsRTX 5090NVIDIA · 32 GB VRAM · GPU

▲ 25× prompts▲ 879% speed▲ 3.5 GB$5,502rent $0.50/hr

Mac Mini M6 tokens per second by model size

Output speed depends on memory bandwidth (170 GB/s). Grey rows need more than the 28.5 GB available.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
18.7tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
12.5tok/s
27–31BQwen3.8 27B · Q4_K_M · 17.9 GB slow
6.8tok/s
35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
30.9tok/s
70BLlama 3.3 70B Instruct · not at 4-bit
needs 51.3 GB
120B MoEGPT OSS 120B · not at 4-bit
needs 70.8 GB

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

Chip generations: writing vs compute

M1 → M5

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

Writing speed follows memory bandwidth and barely moved: 7.5 to 16.9 tok/s since the M1. Compute, which sets how fast prompts are read, grew 3.1×. Indexed to the M1; speeds on Qwen3.5 9B, same 16 GB.

All 343 models on the Mac Mini M6

Featured only

Best quant that fits in 28.5 GB, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works

LLM models compatible with Mac Mini M6 (32 GB) — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Unlimited OCR 23.3BVision Q4_K_M·106.2 t/s	Q4_K_M	3.3 GB12%	106.2 t/s	131K	S92, Runs great
Holo4 27B27.4BVisionFunctions Q4_K_M·6.9 t/s	Q4_K_M	17.6 GB62%	6.9 t/s	262K	C44, Usable
Qwen3 30B A3B Thinking 250730.5BChatFunctions Q4_K_M·37.2 t/s	Q4_K_M	19.4 GB68%	37.2 t/s	262K	A74, Runs well
InternVL3 1B938MVision Q4_K_M·191.9 t/s	Q4_K_M	2.0 GB7%	191.9 t/s	—	S99, Runs great
LensVLM 9B9.4BVisionFunctions Q4_K_M·19.2 t/s	Q4_K_M	6.5 GB23%	19.2 t/s	262K	B59, Decent
Qwen3 Coder 30B A3B Instruct30.5BChatCodeFunctions Q4_K_M·37.2 t/s	Q4_K_M	19.4 GB68%	37.2 t/s	262K	A74, Runs well
Qwen AgentWorld 35B A3B34.7BChatFunctions Q4_K_M·38.8 t/s	Q4_K_M	21.3 GB75%	38.8 t/s	262K	A75, Runs well
Ornith 1.5 9B9.7BChatFunctions Q4_K_M·18.7 t/s	Q4_K_M	6.6 GB23%	18.7 t/s	262K	B58, Decent
LFM2.5 8B A1B8.5BChatFunctions Q4_K_M·71.6 t/s	Q4_K_M	5.6 GB20%	71.6 t/s	128K	S86, Runs great
SmolLM3 3B3.1BChatFunctions Q4_K_M·51.7 t/s	Q4_K_M	3.4 GB12%	51.7 t/s	66K	A80, Runs well
SmolVLM 256M Instruct256MVision Q4_K_M·238.0 t/s	Q4_K_M	0.6 GB2%	238.0 t/s	8K	S100, Runs great
SmolVLM 500M Instruct507MVision Q4_K_M·172.5 t/s	Q4_K_M	0.9 GB3%	172.5 t/s	8K	S98, Runs great
Molmo2 4B4.9BVision Q4_K_M·35.0 t/s	Q4_K_M	4.7 GB17%	35.0 t/s	37K	A73, Runs well
LFM2.5 2.6B2.7BChatFunctions Q4_K_M·58.3 t/s	Q4_K_M	2.3 GB8%	58.3 t/s	131K	A83, Runs well
Qwen3 30B A3B Instruct 250730.5BChatFunctions Q4_K_M·37.2 t/s	Q4_K_M	19.4 GB68%	37.2 t/s	262K	A74, Runs well

Mac Mini M6 specs

Specs

Chip: M6
CPU cores: 12
GPU cores: 12
Unified memory: 32 GB
For models: 28.5 GB (macOS keeps 3.5 GB)
Memory bandwidth: 170 GB/s
FP16 (dense): 19.2 TFLOPS
Neural Engine: 76 TOPS
Released: 2026-09-22
MSRP: $1,299

Mac Mini M6 FAQ

Is the Mac Mini M6 (32 GB) worth it for local LLMs in 2026?

At its $1,299 MSRP it gives 14.4 tok/s per $1,000 on Qwen3.5 9B, 5th of the 6 machines compared here. It runs 9B and 35B MoE models well; 14B and 27–31B fit but are slow (13 and 7 tok/s), and 70B doesn't fit in 28.5 GB.

How much memory is available for AI on the Mac Mini M6 (32 GB)?

About 28.5 GB of the 32 GB. macOS keeps roughly 3.5 GB for itself and other apps.

What is the largest model the Mac Mini M6 (32 GB) can run?

Qwen3.6 35B A3B (36.0B) is the largest at 4-bit or better: at Q4_K_M it uses 22.0 GB, 77% of the available memory, and runs at about 30.9 tok/s.

Can the Mac Mini M6 (32 GB) run 70B models?

No. Llama 3.3 70B Instruct needs 51.3 GB at Q4, more than the 28.5 GB available.

How long does the Mac Mini M6 (32 GB) take to read a long prompt?

On Qwen3.6 35B A3B, about 10 s for a 4K-token prompt and 81 s for a 32K-token document before the first word appears.

Is renting a GPU cheaper than buying the Mac Mini M6?

An A100 (40 GB) rents from $0.58/hr. Renting costs as much as buying after ≈2,200 hours (≈1.5 years at 4 h a day).

24 GB GPUs All Macs Desktops & mini PCs Mac Studio M1 Max Mac Studio M2 Max MacBook Pro 14" M1 Max MacBook Pro 14" M2 Max MacBook Pro 16" M1 Max MacBook Pro 16" M2 Max MacBook Pro 14" M3 Max MacBook Pro 16" M4 Max Best coding LLMs All hardware