Can Qwen 2.5 VL 72B run on Mac Studio M3 Ultra 96GB?

YES — Tight Fit

S88Excellent

○Estimated from fit model

Qwen 2.5 VL 72B needs ~60.1 GB VRAM. Mac Studio M3 Ultra 96GB has 69.1 GB. With Q4_K_M quantization, expect ~13 tok/s.

Runtime: llama.cppCapacity: TightBandwidth: HighStack: StandardBottleneck: Balanced

Operating mode

Choose the run profile you care about

Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 60.1 GB, 13.8 tok/s, Tight fit

60.1 GB required69.1 GB available

87% VRAM used

Fit status

Tight fit

Decode

13.8 tok/s

TTFT

14039 ms

Safe context

33K

Memory

60.1 GB / 69.1 GB

Memory breakdown

Weights43.9 GB

KV Cache4.9 GB

Runtime0.9 GB

Headroom10.4 GB

See how fast it feels

See how fast it feelsQwen 2.5 VL 72B on Mac Studio M3 Ultra 96GB
1st promptCold start — includes initialization
>Solve: If a train travels at 60 mph for 2.5 hours, how far does it go?
Let me work through this step by step.

Given information:
 - Speed = 60 mph (miles per hour)
 - Time = 2.5 hours

Formula: Distance = Speed x Time

Calculation:
 Distance = 60 mph x 2.5 h
 = 150 miles

The train travels 150 miles.

Double-check: at 60 mph the train covers 60 miles each hour. In half an hour it covers 30 miles. So in 2.5 hours: 60 + 60 + 30 = 150 miles. Confirmed.
2nd promptWarm — model ready, no init overhead
>What if the train stops for 20 minutes halfway?
The stop doesn't change the total distance covered while moving, but it affects total trip time.

Breakdown:
 - First half: 1.25 hours at 60 mph = 75 miles
 - Stop: 20 minutes (no distance)
 - Second half: 1.25 hours at 60 mph = 75 miles

Total distance: 150 miles (same)
Total time: 2.5 h + 0.33 h = 2.83 hours
Average speed: 150 / 2.83 = 53 mph

The distance stays the same but average speed drops to 53 mph because of the stop.
Estimated: 13.8 tok/s decode · 14.0s TTFT (warm) · 35 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

Shared-memory contention still exists

The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	S	Tight fit	12.7 tok/s	8328 ms	33K
Coding	S	Tight fit	12.7 tok/s	15268 ms	33K
Agentic Coding	S	Tight fit	12.7 tok/s	22208 ms	33K
Reasoning	S	Tight fit	12.7 tok/s	18044 ms	33K
RAG	S	Tight fit	12.7 tok/s	27760 ms	33K

Quantization options

How Qwen 2.5 VL 72B (72B params) fits at each quantization level on Mac Studio M3 Ultra 96GB (69.1 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	28.1 GB	Low	S86
Q3_K_S	3	35.3 GB	Low	S88
NVFP4	4

Get started

Copy-paste commands to run Qwen 2.5 VL 72B on your machine.

Run

lms load Qwen2.5-VL-72B-Instruct && lms server start

Your hardware

More models your Mac Studio M3 Ultra 96GB can run

Model	Params	Grade	Decode	Capabilities
👁 Cohere Command A 111B	111B	A	6.8 tok/s

Frequently asked questions

See all results for Mac Studio M3 Ultra 96GB See all hardware for Qwen 2.5 VL 72B

URL: https://willitrunai.com/can-run/qwen-2.5-vl-72b-on-m3-ultra-96gb

⇱