Apple · M5 Ultra · Desktop

Best AI Models for Mac Studio M5 Ultra (256 GB)

Runs 70–120B models well; fits models up to 427B, like MiniMax M3.

256 GB unified252.5 GB for models1.2 TB/s109 TFLOPS FP162026

Memory

96 GB$5,499 256 GB$9,499 512 GB$22,299

What LLMs can the Mac Studio M5 Ultra run?

#	Model	Speed	Quant · Memory
1	MiMo V2.6 Flash RLXiaomiHow to run → Q4_K_M · 186.5 GB · 49.8 t/s	49.8 tok/s	Q4_K_M · 186.5 GB
2	DeepSeek V4 Flash 0731DeepSeek Q4_K_M · 183.0 GB · 36.1 t/s	36.1 tok/s	Q4_K_M · 183.0 GB
3	GLM 5.3 FlashZ.ai Q4_K_M · 205.2 GB · 45.6 t/s	45.6 tok/s	Q4_K_M · 205.2 GB
4	Qwen3.8 27BAlibaba Q4_K_M · 17.9 GB · 49.3 t/s	49.3 tok/s	Q4_K_M · 17.9 GB
5	Hy3Tencent Q4_K_M · 182.3 GB · 32.6 t/s	32.6 tok/s	Q4_K_M · 182.3 GB

#	Model	Speed	Quant · Memory
1	MiMo V2.6 Flash RLXiaomiHow to run → Q4_K_M · 186.5 GB · 49.8 t/s	49.8 tok/s	Q4_K_M · 186.5 GB
2	DeepSeek V4 Flash 0731DeepSeek Q4_K_M · 183.0 GB · 36.1 t/s	36.1 tok/s	Q4_K_M · 183.0 GB
3	Qwen3.8 27BAlibaba Q4_K_M · 17.9 GB · 49.3 t/s	49.3 tok/s	Q4_K_M · 17.9 GB
4	GLM 5.3 FlashZ.ai Q4_K_M · 205.2 GB · 45.6 t/s	45.6 tok/s	Q4_K_M · 205.2 GB
5	Hy3Tencent Q4_K_M · 182.3 GB · 32.6 t/s	32.6 tok/s	Q4_K_M · 182.3 GB

#	Model	Speed	Quant · Memory
1	DeepSeek V4 Flash 0731DeepSeekHow to run → Q4_K_M · 183.0 GB · 36.1 t/s	36.1 tok/s	Q4_K_M · 183.0 GB
2	GLM 5.3 FlashZ.ai Q4_K_M · 205.2 GB · 45.6 t/s	45.6 tok/s	Q4_K_M · 205.2 GB
3	Qwen3.8 27BAlibaba Q4_K_M · 17.9 GB · 49.3 t/s	49.3 tok/s	Q4_K_M · 17.9 GB
4	Inkling SmallThinking Machines Q4_K_M · 162.7 GB · 104 t/s	104 tok/s	Q4_K_M · 162.7 GB
5	Hy3Tencent Q4_K_M · 182.3 GB · 32.6 t/s	32.6 tok/s	Q4_K_M · 182.3 GB

#	Model	Speed ↓	Quant · Memory
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 264 t/s	264 tok/s	Q4_K_M · 3.4 GB
2	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 135 t/s	135 tok/s	Q4_K_M · 6.6 GB
3	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 128 t/s	128 tok/s	Q4_K_M · 13.1 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 109 t/s	109 tok/s	Q4_K_M · 16.5 GB
5	Hy3Tencent Q4_K_M · 182.3 GB · 32.6 t/s	32.6 tok/s	Q4_K_M · 182.3 GB

#	Model	Speed	Quant · Memory
1	GLM 5.3 FlashZ.aiHow to run → Q4_K_M · 205.2 GB · 45.6 t/s	45.6 tok/s	Q4_K_M · 205.2 GB
2	Qwen3.8 27BAlibaba Q4_K_M · 17.9 GB · 49.3 t/s	49.3 tok/s	Q4_K_M · 17.9 GB
3	Inkling SmallThinking Machines Q4_K_M · 162.7 GB · 104 t/s	104 tok/s	Q4_K_M · 162.7 GB
4	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 49.3 t/s	49.3 tok/s	Q4_K_M · 17.9 GB
5	Muse Glimmer 30BMeta Q4_K_M · 19.6 GB · 46.9 t/s	46.9 tok/s	Q4_K_M · 19.6 GB

#	Model	Speed	Quant · Memory
1	GLM 5.3 FlashZ.aiHow to run → Q4_K_M · 205.2 GB · 45.6 t/s	45.6 tok/s	Q4_K_M · 205.2 GB
2	Qwen3.8 27BAlibaba Q4_K_M · 17.9 GB · 49.3 t/s	49.3 tok/s	Q4_K_M · 17.9 GB
3	MiniMax M2.7MiniMax Q4_K_M · 139.6 GB · 49.7 t/s	49.7 tok/s	Q4_K_M · 139.6 GB
4	GLM 4.5Z.ai Q4_K_M · 217.9 GB · 23.1 t/s	23.1 tok/s	Q4_K_M · 217.9 GB
5	Hy3Tencent Q4_K_M · 182.3 GB · 32.6 t/s	32.6 tok/s	Q4_K_M · 182.3 GB

See all 429 models on the Mac Studio M5 Ultra →Bars = traction for models without a Score yet

About the Mac Studio M5 Ultra (256 GB)

The Mac Studio M5 Ultra is the fastest 256 GB machine: it runs 70–120B models well. macOS keeps about 3.5 GB, leaving 252.5 GB for models. With 109 TFLOPS it reads long prompts faster than most 256 GB machines: a 4K-token prompt takes 5.7 s. At its $9,499 MSRP it gives 9.3 tok/s per $1,000, 5th of the 7 machines compared here. M5 Ultra generation, released 2026.

Speed in 256 GB#11.2 TB/s

Prompt reading#1109 TFLOPS

For models252.5 GBmacOS keeps 3.5 GB

ChipM5 Ultrareleased 2026

Mac Studio M5 Ultra strengths and weaknesses

Strengths

Runs 120B MoE models: GPT OSS 120B at 89.0 tok/s in 70.8 GB
Room for long context: Llama 3.3 70B Instruct at Q4 uses 51.3 GB, leaving 201.2 GB free

Weaknesses

Slow prompt reading: A 32K-token prompt on MiMo V2.6 Flash RL waits 45.0 s for the first token
No CUDA: vLLM, AWQ, GPTQ and FP8 builds don't run; use GGUF or MLX

Memory for models

252.5 GB of 256 GB

35B MoE22 GB70B51.3 GB120B MoE70.8 GB427B242 GB

120B MoE70.8 GB427B242 GB

For models 252.5 GBmacOS keeps 3.5 GBModel size at Q4

Everything on the size ladder fits. MiMo V2.6 Flash RL and Qwen3.8 27B together use 204.4 GB and leave 48.1 GB free.

Speed per dollar and per watt

NewUsed

On Qwen3.6 35B A3B (35B params, 3B active) 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 Studio M5 Ultra 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	213	38.8	37.1
Mac Studio M5 Ultra96 GB	about $5,499	87.9	16.0	–
Mac Studio M2 Ultra192 GB	about $5,599	75.9	13.6	25.7
Mac Studio M3 Ultra256 GB	about $7,099	76.6	10.8	28.4
Mac Studio M5 Ultra256 GB	about $9,499	87.9	9.3	–
Mac Studio M3 Ultra512 GB	about $9,499	76.6	8.1	28.4
Mac Studio M5 Ultra512 GB	about $22,299	87.9	3.9	–

Machine	Used price	tok/s	tok/s per $1,000	tok/s per 100 W
RTX 409024 GB	about $3,000	151	50.3	33.6
RTX 509032 GB	about $7,000	213	30.5	37.1

Cost per token: the Mac Studio M5 Ultra against 24–512 GB machines and GPUs

On Qwen3.6 35B A3B (35B params, 3B active, Q4_K_M, 4K context). Speed, cost per token and power per token depend on the model.

NewUsed

Speed$ per 1M tokens

24–36 GB96–128 GB192+ GBthis desktopat MSRP

Cost per 1M output tokenson Qwen3.6 35B A3B · card over 3 years + power

$6.85

Machine, MSRP: $6.85
Power: not published

3-year cost of ownership$9,499

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 Qwen3.6 35B A3B.

Same chip, 160 GB less memory for $4,000 lessMac Studio M5 Ultra (96 GB)Apple · 92.5 GB for models · M5 Ultra

same speed▼ $4,000 less▼ 160 GB$5,499

Same family Same chip, 2× the memory for $12,800 moreMac Studio M5 Ultra (512 GB)Apple · 508.5 GB for models · M5 Ultra

same speed▲ $12,800 more▲ 256 GB$22,299

Same family Machine, 13% slowerMac Studio M3 Ultra (256 GB)Apple · 252.5 GB for models · M3 Ultra

▼ 13% speedsame memory$7,099

Machine, 14% slowerMac Studio M2 Ultra (192 GB)Apple · 188.5 GB for models · M2 Ultra

▼ 14% speed▼ 64 GB$5,599

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

▲ 72% speed▼ 228.5 GB$1,599rent $0.34/hr

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

▲ 143% speed▼ 220.5 GB$5,502rent $0.50/hr

Mac Studio M5 Ultra tokens per second by model size

Output speed depends on memory bandwidth (1228 GB/s). Grey rows need more than the 252.5 GB available.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
135tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
90.5tok/s
27–31BQwen3.8 27B · Q4_K_M · 17.9 GB
49.3tok/s
35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
87.9tok/s
70BLlama 3.3 70B Instruct · Q4_K_M · 51.3 GB
18.5tok/s
120B MoEGPT OSS 120B · Q4_K_M · 70.8 GB
89.0tok/s

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

Ultra generations: writing vs compute

M1 Ultra → M5 Ultra

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

Writing speed follows memory bandwidth and barely moved: 75.9 to 87.9 tok/s since the M1 Ultra. Compute, which sets how fast prompts are read, grew 3.5×. Indexed to the M1 Ultra; speeds on Qwen3.6 35B A3B, same 128 GB.

All 1346 models on the Mac Studio M5 Ultra

Featured only

Best quant that fits in 252.5 GB, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works

LLM models compatible with Mac Studio M5 Ultra (256 GB) — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Clef Omni35.3BVisionFunctions Q4_K_M·82.4 t/s	Q4_K_M	27.2 GB11%	82.4 t/s	—	S88, Runs great
MiMo V2.5310.8BChatFunctions Q4_K_M·45.9 t/s	Q4_K_M	187.6 GB74%	45.9 t/s	1049K	A78, Runs well
Diffusiongemma 26B A4B IT25.8BVisionFunctions Q4_K_M·108.6 t/s	Q4_K_M	16.5 GB7%	108.6 t/s	262K	S93, Runs great
Qwen3.8 27B DSpark1.9BChat Q4_K_M·588.8 t/s	Q4_K_M	1.8 GB1%	588.8 t/s	262K	S100, Runs great
Ling Flash 2.0102.9BChatFunctions Q4_K_M·93.2 t/s	Q4_K_M	63.1 GB25%	93.2 t/s	33K	S90, Runs great
Olmo 3.1 32B Instruct32.2BChatFunctions Q4_K_M·42.6 t/s	Q4_K_M	21.5 GB9%	42.6 t/s	66K	A76, Runs well
Phi 414.7BChatMathCode Q4_K_M·90.3 t/s	Q4_K_M	12.5 GB5%	90.3 t/s	16K	S90, Runs great
NVIDIA Nemotron 3.5 Bolt E4B 4GB4BChat Q4_K_M·325.6 t/s	Q4_K_M	4.8 GB2%	325.6 t/s	—	S100, Runs great
JevK54.2BChatFunctions Q4_K_M·287.5 t/s	Q4_K_M	3.2 GB1%	287.5 t/s	262K	S100, Runs great
DeepSeek V4 Flash 0731 Abliterated305.7BChat Q4_K_M·34.7 t/s	Q4_K_M	183.9 GB73%	34.7 t/s	1049K	A73, Runs well
OTel 2.0 LLM 31B IT QLoRA31.3BChat BF16·12.5 t/s	BF16	72.6 GB29%	12.5 t/s	—	B51, Decent
DeepSeek V4 Flash Vision Exp304.6BVision Q4_K_M·51.9 t/s	Q4_K_M	183.3 GB73%	51.9 t/s	1049K	A81, Runs well
Qwen3.8 4B Distill4.7BChatReasoningFunctions Q4_K_M·263.7 t/s	Q4_K_M	3.4 GB1%	263.7 t/s	262K	S100, Runs great
Agents A135.1BChatVisionFunctions Q4_K_M·92.8 t/s	Q4_K_M	21.5 GB9%	92.8 t/s	262K	S90, Runs great
Llm Jp 4.1 32B A3b Thinking32.1BChatFunctions Q4_K_M·109.6 t/s	Q4_K_M	20.1 GB8%	109.6 t/s	66K	S93, Runs great

Mac Studio M5 Ultra specs

Specs

Chip: M5 Ultra
CPU cores: 30
GPU cores: 64
Unified memory: 256 GB
For models: 252.5 GB (macOS keeps 3.5 GB)
Memory bandwidth: 1.2 TB/s
FP16 (dense): 108.8 TFLOPS
Neural Engine: 76 TOPS
Released: 2026-09-22
MSRP: $9,499

Mac Studio M5 Ultra FAQ

Is the Mac Studio M5 Ultra (256 GB) worth it for local LLMs in 2026?

At its $9,499 MSRP it gives 9.3 tok/s per $1,000 on Qwen3.6 35B A3B, 5th of the 7 machines compared here. It runs 70–120B models well; fits models up to 427B, like MiniMax M3.

How much memory is available for AI on the Mac Studio M5 Ultra (256 GB)?

About 252.5 GB of the 256 GB. macOS keeps roughly 3.5 GB for itself and other apps.

What is the largest model the Mac Studio M5 Ultra (256 GB) can run?

MiniMax M3 (427.0B) is the largest at 4-bit or better: at Q4_K_S it uses 242.0 GB, 96% of the available memory, and runs at about 40.0 tok/s.

Can the Mac Studio M5 Ultra (256 GB) run MiMo V2.6 Flash RL?

Yes. MiMo V2.6 Flash RL fits at Q4_K_M, using 186.5 GB of the 252.5 GB available, and it is the best model that runs well on this machine.

How long does the Mac Studio M5 Ultra (256 GB) take to read a long prompt?

On MiMo V2.6 Flash RL, about 5.7 s for a 4K-token prompt and 45 s for a 32K-token document before the first word appears.

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