VOOZH about

URL: https://willitrunai.com/can-run/qwen-2.5-72b-on-m2-ultra-128gb

⇱ Qwen 2.5 72B on Mac Studio M2 Ultra 128GB? YES

Can Qwen 2.5 72B run on Mac Studio M2 Ultra 128GB?

YES — Runs Great

A81Great
○Estimated from fit model

Qwen 2.5 72B needs ~63.5 GB VRAM. Mac Studio M2 Ultra 128GB has 92.2 GB. With Q4_K_M quantization, expect ~12 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: Balanced
Share:

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) — 63.5 GB, 11.5 tok/s, Runs well
63.5 GB required92.2 GB available
69% VRAM used

Fit status

Runs well

Decode

11.5 tok/s

TTFT

16851 ms

Safe context

110K

Memory

63.5 GB / 92.2 GB

Memory breakdown

Weights43.9 GB
KV Cache4.9 GB
Runtime0.9 GB
Headroom13.8 GB

See how fast it feels

See how fast it feelsQwen 2.5 72B on Mac Studio M2 Ultra 128GB
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: 11.5 tok/s decode · 16.9s TTFT (warm) · 29 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

WorkloadGradeFitDecodeTTFTContext
ChatARuns well11.5 tok/s9191 ms110K
CodingARuns well11.5 tok/s16851 ms110K
Agentic CodingARuns well11.5 tok/s24510 ms110K
ReasoningARuns well11.5 tok/s19915 ms110K
RAGARuns well11.5 tok/s30638 ms110K

Quantization options

How Qwen 2.5 72B (72B params) fits at each quantization level on Mac Studio M2 Ultra 128GB (92.2 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
28.1 GB
LowA74
Q3_K_S
3
35.3 GB
LowA75
NVFP4
4
40.3 GB
MediumA77
Q4_K_M
4
43.9 GB
MediumA77
Q5_K_M
5
51.8 GB
HighA79
Q6_K
6
59.0 GB
HighA79
Q8_0Best for your GPU
8
77.0 GB
Very HighA79
F16
16
147.6 GB
MaximumF0

Get started

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

Run

ollama run qwen2.5:72b

Your hardware

More models your Mac Studio M2 Ultra 128GB can run

ModelParamsGradeDecodeCapabilities
👁 Mistral
Devstral 2 123B Instruct		123BS6.3 tok/s
👁 Alibaba
Qwen 3.5 122B A10B		122BS28.9 tok/s
👁 Mistral
Mistral Small 4 119B		119BS30.8 tok/s
👁 OpenAI
GPT-OSS 120B		117BS7.1 tok/s
👁 Cohere
Command A 111B		111BS7.5 tok/s

Frequently asked questions

See all results for Mac Studio M2 Ultra 128GBSee all hardware for Qwen 2.5 72B