Apple · M2 Ultra · Desktop

Best AI Models for Mac Pro M2 Ultra (192 GB)

Runs 27–31B and 120B MoE models well; dense 70B fits but is slow at 12 tok/s.

192 GB unified188.5 GB for models800 GB/s54 TFLOPS FP162023

Memory

Same chip in

What LLMs can the Mac Pro M2 Ultra run?

#	Model	Speed	Quant · Memory
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 32.1 t/s	32.1 tok/s	Q4_K_M · 17.9 GB
2	Inkling SmallThinking Machines Q4_K_M · 162.7 GB · 97.6 t/s	97.6 tok/s	Q4_K_M · 162.7 GB
3	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 32.1 t/s	32.1 tok/s	Q4_K_M · 17.9 GB
4	MiniMax M2.7MiniMax Q4_K_M · 139.6 GB · 41.2 t/s	41.2 tok/s	Q4_K_M · 139.6 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 77.0 t/s	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 t/s	32.1 tok/s	Q4_K_M · 17.9 GB
2	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 27.5 t/s	27.5 tok/s	Q4_K_M · 21.7 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 75.9 t/s	75.9 tok/s	Q4_K_M · 22.0 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 91.7 t/s	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 t/s	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 t/s	32.1 tok/s	Q4_K_M · 17.9 GB
2	Inkling SmallThinking Machines Q4_K_M · 162.7 GB · 97.6 t/s	97.6 tok/s	Q4_K_M · 162.7 GB
3	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 27.5 t/s	27.5 tok/s	Q4_K_M · 21.7 GB
4	Qwen3.5 27BAlibaba Q4_K_M · 17.9 GB · 32.1 t/s	32.1 tok/s	Q4_K_M · 17.9 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 77.0 t/s	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 t/s	32.1 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 32.1 t/s	32.1 tok/s	Q4_K_M · 17.9 GB
3	MiniMax M2.7MiniMax Q4_K_M · 139.6 GB · 41.2 t/s	41.2 tok/s	Q4_K_M · 139.6 GB
4	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 27.5 t/s	27.5 tok/s	Q4_K_M · 21.7 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 77.0 t/s	77.0 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed ↓	Quant · Memory
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 172 t/s	172 tok/s	Q4_K_M · 3.4 GB
2	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 106 t/s	106 tok/s	Q4_K_M · 13.1 GB
3	Inkling SmallThinking Machines Q4_K_M · 162.7 GB · 97.6 t/s	97.6 tok/s	Q4_K_M · 162.7 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 91.7 t/s	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 t/s	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 t/s	32.1 tok/s	Q4_K_M · 17.9 GB
2	MiniMax M2.7MiniMax Q4_K_M · 139.6 GB · 41.2 t/s	41.2 tok/s	Q4_K_M · 139.6 GB
3	MiniMax M2MiniMax Q4_K_M · 139.6 GB · 41.2 t/s	41.2 tok/s	Q4_K_M · 139.6 GB
4	Qwen2.5 Coder 32B InstructAlibaba Q4_K_M · 24.3 GB · 27.3 t/s	27.3 tok/s	Q4_K_M · 24.3 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 77.0 t/s	77.0 tok/s	Q4_K_M · 19.3 GB

See all 411 models on the Mac Pro M2 Ultra →Bars = traction for models without a Score yet

About the Mac Pro M2 Ultra (192 GB)

The Mac Pro M2 Ultra runs 27–31B and 120B MoE models well. macOS keeps about 3.5 GB, leaving 188.5 GB for models. Prompt reading is its weak spot: a 4K-token prompt waits 21 s before the first word on Qwen3.8 27B. M2 Ultra generation, released 2023; the newer M3 Ultra writes 1% faster with 1.2× the compute.

For models188.5 GBmacOS keeps 3.5 GB

ChipM2 Ultrareleased 2023

Mac Pro M2 Ultra strengths and weaknesses

Strengths

Runs 120B MoE models: GPT OSS 120B at 74.6 tok/s in 70.8 GB
Room for long context: Qwen3.8 27B at Q4 uses 17.9 GB, leaving 170.6 GB free

Weaknesses

Slow prompt reading: A 32K-token prompt on Qwen3.8 27B waits 2.8 min for the first token
No CUDA: vLLM, AWQ, GPTQ and FP8 builds don't run; use GGUF or MLX

Memory for models

188.5 GB of 192 GB

35B MoE22 GB70B51.3 GB120B MoE70.8 GB309B186.5 GB

120B MoE70.8 GB309B186.5 GB

For models 188.5 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 152.8 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, 64 GB less memoryMac Pro M2 Ultra (128 GB)Apple · 124.5 GB for models · M2 Ultra

same speed▼ 64 GBno price

Same family Same chip, 128 GB less memoryMac Pro M2 Ultra (64 GB)Apple · 60.5 GB for models · M2 Ultra

same speed▼ 128 GBno price

Same family Newer machine, as fastMac Studio M3 Ultra (256 GB)Apple · 252.5 GB for models · M3 Ultra

same speed▲ 64 GB$7,099

Newer machine, 15% slowerMac Studio M4 Max (128 GB)Apple · 124.5 GB for models · M4 Max

▼ 15% speed▼ 64 GB$3,499

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

▲ 99% speed▼ 164.5 GB$1,599rent $0.34/hr

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

▲ 181% speed▼ 156.5 GB$5,376rent $0.50/hr

Mac Pro M2 Ultra tokens per second by model size

Output speed depends on memory bandwidth (800 GB/s). Grey rows need more than the 188.5 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_K_M · 70.8 GB
74.6tok/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 2.1×. Indexed to the M1 Ultra; speeds on Qwen3.6 35B A3B, same 128 GB.

All 1309 models on the Mac Pro M2 Ultra

Featured only

Best quant that fits in 188.5 GB, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works

LLM models compatible with Mac Pro M2 Ultra (192 GB) — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Supra2 100M Instruct101MChat Q4_K_M·1435.9 t/s	Q4_K_M	0.4 GB0%	1435.9 t/s	2K	S100, Runs great
Sevclassifier Jev Style 1.5B1.5BChatFunctions Q4_K_M·437.5 t/s	Q4_K_M	1.7 GB1%	437.5 t/s	33K	S100, Runs great
Ornith 1.5 9B9.7BChatFunctions Q4_K_M·88.1 t/s	Q4_K_M	6.6 GB4%	88.1 t/s	262K	S89, Runs great
Beam 1.0 501B A23B501.3BChatReasoningCodeFunctions IQ2_M·40.7 t/s	IQ2_M	172.4 GB91%	40.7 t/s	1049K	B60, Decent
QwQ 32B32.8BChatReasoningFunctions Q4_K_M·27.3 t/s	Q4_K_M	24.3 GB13%	27.3 t/s	41K	A68, Runs well
Crowd V11.0BChatFunctions BF16·252.3 t/s	BF16	3.7 GB2%	252.3 t/s	—	S100, Runs great
Qwen3.5 35B A3B36.0BVision Q4_K_M·75.9 t/s	Q4_K_M	22.0 GB12%	75.9 t/s	262K	S87, Runs great
Llm Jp 4.1 32B A3b Thinking32.1BChatFunctions Q4_K_M·94.5 t/s	Q4_K_M	20.1 GB11%	94.5 t/s	66K	S90, Runs great
SmolLM3 3B3.1BChatFunctions Q4_K_M·243.5 t/s	Q4_K_M	3.4 GB2%	243.5 t/s	66K	S100, Runs great
HARP 1B123MChatCode Q4_K_M·1435.9 t/s	Q4_K_M	0.4 GB0%	1435.9 t/s	1K	S100, Runs great
DeepSeek V4 Flash Vision Exp304.6BVision Q4_K_M·40.1 t/s	Q4_K_M	183.3 GB97%	40.1 t/s	1049K	B49, Decent
Phi 414.7BChatMathCode Q4_K_M·58.8 t/s	Q4_K_M	12.5 GB7%	58.8 t/s	16K	A83, Runs well
Beetle Monolingual Fineweb3 Eng194MChat BF16·1302.3 t/s	BF16	0.4 GB0%	1302.3 t/s	1K	S100, Runs great
Wald 4B4.7BChatReasoningFunctions Q4_K_M·171.8 t/s	Q4_K_M	3.4 GB2%	171.8 t/s	262K	S98, Runs great
Tiny Lfm2ForCausalLM 2.5526340ChatFunctions Q4_K_M·1866.7 t/s	Q4_K_M	0.5 GB0%	1866.7 t/s	128K	S100, Runs great

Mac Pro M2 Ultra specs

Specs

Chip: M2 Ultra
CPU cores: 24
GPU cores: 76
Unified memory: 192 GB
For models: 188.5 GB (macOS keeps 3.5 GB)
Memory bandwidth: 800 GB/s
FP16 (dense): 54.4 TFLOPS
Neural Engine: 32 TOPS
Released: 2023-06-13

Mac Pro M2 Ultra FAQ

How much memory is available for AI on the Mac Pro M2 Ultra (192 GB)?

About 188.5 GB of the 192 GB. macOS keeps roughly 3.5 GB for itself and other apps.

What is the largest model the Mac Pro M2 Ultra (192 GB) can run?

MiMo V2.6 Flash RL (309B) is the largest at 4-bit or better: at Q4_K_M it uses 186.5 GB, 99% of the available memory, and runs at about 38.9 tok/s.

Can the Mac Pro M2 Ultra (192 GB) run Qwen3.8 27B?

Yes. Qwen3.8 27B fits at Q4_K_M, using 17.9 GB of the 188.5 GB available, and it is the best model that runs well on this machine.

How long does the Mac Pro M2 Ultra (192 GB) take to read a long prompt?

On Qwen3.8 27B, about 21 s for a 4K-token prompt and 2.8 min for a 32K-token document before the first word appears.

Is renting a GPU cheaper than buying the Mac Pro M2 Ultra?

An RTX PRO 6000 Blackwell Workstation Edition (96 GB) rents from $1.14/hr.

48 GB GPUs All Macs Desktops & mini PCs Best coding LLMs All hardware