Apple · M1 Ultra · Desktop

Best AI Models for Mac Studio M1 Ultra (64 GB)

Runs 27–35B models well and fits 120B MoE; dense 70B fits but is slow at 12 tok/s.

64 GB unified60.5 GB for models800 GB/s31 TFLOPS FP162022

Memory

What LLMs can the Mac Studio M1 Ultra run?

#	Model	Speed	Quant · Memory
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB	32.1 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB	32.1 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB	27.5 tok/s	Q4_K_M · 21.7 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB	91.7 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB	77.0 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · Memory
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB	32.1 tok/s	Q4_K_M · 17.9 GB
2	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB	27.5 tok/s	Q4_K_M · 21.7 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB	75.9 tok/s	Q4_K_M · 22.0 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB	91.7 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB	77.0 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · Memory
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB	32.1 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.5 27BAlibaba Q4_K_M · 17.9 GB	32.1 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB	27.5 tok/s	Q4_K_M · 21.7 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB	91.7 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB	77.0 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Math Score	Quant · Memory
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB	32.1 tok/s		Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB	32.1 tok/s		Q4_K_M · 17.9 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB	75.9 tok/s		Q4_K_M · 22.0 GB
4	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB	27.5 tok/s	overall	Q4_K_M · 21.7 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB	77.0 tok/s		Q4_K_M · 19.3 GB

#	Model	Speed ↓	Quant · Memory
1	GPT OSS 20BOpenAIHow to run → Q4_K_M · 13.1 GB	106 tok/s	Q4_K_M · 13.1 GB
2	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB	91.7 tok/s	Q4_K_M · 16.5 GB
3	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB	88.1 tok/s	Q4_K_M · 6.6 GB
4	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB	77.0 tok/s	Q4_K_M · 19.3 GB
5	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB	75.9 tok/s	Q4_K_M · 22.0 GB

See all 338 models on the Mac Studio M1 Ultra →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 Studio M1 Ultra (64 GB)

The Mac Studio M1 Ultra is the fastest 64 GB machine: it runs 27–35B models well and fits 120B MoE. macOS keeps about 3.5 GB, leaving 60.5 GB for models. Prompt reading is its weak spot: a 4K-token prompt waits 36 s before the first word on Qwen3.8 27B. M1 Ultra generation, released 2022; the newer M2 Ultra writes 0% faster with 1.4× the compute.

Speed in 64 GB#1800 GB/s

Prompt reading#631 TFLOPS

For models60.5 GBmacOS keeps 3.5 GB

ChipM1 Ultrareleased 2022

Mac Studio M1 Ultra strengths and weaknesses

Strengths

Runs 120B MoE models: GPT OSS 120B at 80.8 tok/s in 59.1 GB
Room for long context: Qwen3.8 27B at Q4 uses 17.9 GB, leaving 42.6 GB free

Weaknesses

Slow prompt reading: A 32K-token prompt on Qwen3.8 27B waits 4.9 min for the first token
No CUDA: vLLM, AWQ, GPTQ and FP8 builds don't run; use GGUF or MLX

Memory for models

60.5 GB of 64 GB

9B6.6 GB14B11.9 GB35B MoE22 GB70B51.3 GB120B MoE59.1 GB

35B MoE22 GB120B MoE59.1 GB

For models 60.5 GBmacOS keeps 3.5 GBModel size at Q4

Everything on the size ladder fits. Two 27B-class models together use 35.7 GB and leave 24.8 GB free.

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, 2× the memoryMac Studio M1 Ultra (128 GB)Apple · 124.5 GB for models · M1 Ultra

same speed▲ 64 GBno price

Same family Newer machine, 15% slowerMac Studio M4 Max (64 GB)Apple · 60.5 GB for models · M4 Max

▼ 15% speedsame memory$2,699

Newer machine, as fastMac Studio M3 Ultra (96 GB)Apple · 72 GB for models · M3 Ultra

same speed▲ 11.5 GB$3,999

Newer laptop, 39% slowerMacBook Pro 14 M5 ProApple · 48 GB for models · M5 Pro

▼ 39% speed▼ 12.5 GB$2,299

2.0× faster if your models fit in 24 GBRTX 4090NVIDIA · 24 GB VRAM · GPU

▲ 99% speed▼ 36.5 GB$1,599rent $0.34/hr

2.8× faster if your models fit in 32 GBRTX 5090NVIDIA · 32 GB VRAM · GPU

▲ 181% speed▼ 28.5 GB$5,376rent $0.69/hr

Mac Studio M1 Ultra tokens per second by model size

Output speed depends on memory bandwidth (800 GB/s). Grey rows need more than the 60.5 GB available.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
88.1tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
58.9tok/s
27–31BQwen3.8 27B · Q4_K_M · 17.9 GB
32.1tok/s
35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
75.9tok/s
70BLlama 3.3 70B Instruct · Q4_K_M · 51.3 GB
12.0tok/s
120B MoEGPT OSS 120B · Q4_0 · 59.1 GB tight · Q4_0
80.8tok/s

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

Ultra generations: writing vs compute

M1 Ultra → M3 Ultra

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

Writing speed follows memory bandwidth and barely moved: 75.9 to 76.6 tok/s since the M1 Ultra. Compute, which sets how fast prompts are read, grew 1.4×. Indexed to the M1 Ultra; speeds on Qwen3.6 35B A3B, same 64 GB.

All 1168 models on the Mac Studio M1 Ultra

Featured only

Best quant that fits in 60.5 GB, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works

LLM models compatible with Mac Studio M1 Ultra (64 GB) — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Starcoder15.8BChatCode 15.8B·Q4_K_M·53.6 t/s	Q4_K_M	13.6 GB22%	53.6 t/s	—	A81, Runs well
Qwen2.5 0.5B494MChatFunctions 494M·Q4_K_M·903.2 t/s·33K ctx	Q4_K_M	0.8 GB1%	903.2 t/s	33K	S100, Runs great
Phi 3 Mini 128k Instruct3.8BChatCode 3.8B·Q4_K_M·164.7 t/s·131K ctx	Q4_K_M	9.0 GB15%	164.7 t/s	131K	S97, Runs great
Vlt5 Base Keywords275MChat 275M·BF16·918.0 t/s	BF16	1.6 GB3%	918.0 t/s	—	S100, Runs great
SmolLM2 360M362MChat 362M·Q4_K_M·933.3 t/s·8K ctx	Q4_K_M	0.8 GB1%	933.3 t/s	8K	S100, Runs great
Qwen2 72B Instruct72.7BChat 72.7B·Q4_K_M·12.6 t/s·33K ctx	Q4_K_M	49.3 GB81%	12.6 t/s	33K	B50, Decent
Yi 6B Chat6.1BChat 6.1B·Q4_K_M·137.6 t/s·4K ctx	Q4_K_M	4.2 GB7%	137.6 t/s	4K	S96, Runs great
Qwen3 30B A3B Base30.5BChat 30.5B·Q4_K_M·75.4 t/s·33K ctx	Q4_K_M	19.4 GB32%	75.4 t/s	33K	S86, Runs great
SmolLM 360M362MChat 362M·Q4_K_M·933.3 t/s·2K ctx	Q4_K_M	0.6 GB1%	933.3 t/s	2K	S100, Runs great
Baichuan2 7B Base7BChat 7B·Q4_K_M·121.2 t/s·4K ctx	Q4_K_M	5.0 GB8%	121.2 t/s	4K	S95, Runs great
CodeQwen1.5 7B7.3BChatCode 7.3B·Q4_K_M·117.2 t/s·66K ctx	Q4_K_M	5.7 GB9%	117.2 t/s	66K	S94, Runs great
Yi 9B8.8BChat 8.8B·Q4_K_M·96.6 t/s·4K ctx	Q4_K_M	6 GB10%	96.6 t/s	4K	S90, Runs great
Llama 3.2 1B1.2BChat 1.2B·Q4_K_M·682.9 t/s	Q4_K_M	2.3 GB4%	682.9 t/s	—	S100, Runs great
Qwen2.5 1.5B1.5BChatFunctions 1.5B·Q4_K_M·437.5 t/s·131K ctx	Q4_K_M	1.7 GB3%	437.5 t/s	131K	S100, Runs great
BioMistral 7B7BChat 7B·Q4_K_M·117.4 t/s·33K ctx	Q4_K_M	6.7 GB11%	117.4 t/s	33K	S94, Runs great

Mac Studio M1 Ultra specs

Specs

Chip: M1 Ultra
CPU cores: 20
GPU cores: 48
Unified memory: 64 GB
For models: 60.5 GB (macOS keeps 3.5 GB)
Memory bandwidth: 800 GB/s
FP16 (dense): 31.2 TFLOPS
Neural Engine: 22 TOPS
Released: 2022-03-18

Mac Studio M1 Ultra FAQ

How much memory is available for AI on the Mac Studio M1 Ultra (64 GB)?

About 60.5 GB of the 64 GB. macOS keeps roughly 3.5 GB for itself and other apps.

What is the largest model the Mac Studio M1 Ultra (64 GB) can run?

GPT OSS 120B (116.8B) at Q4_0 uses 59.1 GB, 98% of the available memory, and runs at about 80.8 tok/s.

Can the Mac Studio M1 Ultra (64 GB) run Qwen3.8 27B?

Yes. Qwen3.8 27B fits at Q4_K_M, using 17.9 GB of the 60.5 GB available, and it is the best model that runs well on this machine.

How long does the Mac Studio M1 Ultra (64 GB) take to read a long prompt?

On Qwen3.8 27B, about 36 s for a 4K-token prompt and 4.9 min for a 32K-token document before the first word appears.

Is renting a GPU cheaper than buying the Mac Studio M1 Ultra?

An A100 (80 GB) rents from $0.99/hr.

48 GB GPUs All Macs Desktops & mini PCs Mac Pro M2 Ultra Mac Studio M2 Ultra Mac Studio M5 Max MacBook Pro 14" M5 Max MacBook Pro 16" M5 Max Best coding LLMs All hardware