VOOZH about

URL: https://willitrunai.com/can-run/qwen-2.5-vl-72b-on-gh200-96gb

⇱ Qwen 2.5 VL 72B on NVIDIA GH200 96GB? YES

Can Qwen 2.5 VL 72B run on NVIDIA GH200 96GB?

YES — Runs Great

S95Excellent
○Estimated from fit model

Qwen 2.5 VL 72B needs ~59.3 GB VRAM. NVIDIA GH200 96GB has 96.0 GB. With Q4_K_M quantization, expect ~80 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) — 59.3 GB, 80.2 tok/s, Runs well
59.3 GB required96.0 GB available
62% VRAM used

Fit status

Runs well

Decode

80.2 tok/s

TTFT

2413 ms

Safe context

33K

Memory

59.3 GB / 96.0 GB

Memory breakdown

Weights43.9 GB
KV Cache4.9 GB
Runtime0.9 GB
Headroom9.6 GB

See how fast it feels

See how fast it feelsQwen 2.5 VL 72B on NVIDIA GH200 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: 80.2 tok/s decode · 2.4s TTFT (warm) · 201 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

No major red flags

This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.

Best improvement path

Performance by workload

WorkloadGradeFitDecodeTTFTContext
ChatSRuns well80.2 tok/s1316 ms33K
CodingSRuns well80.2 tok/s2413 ms33K
Agentic CodingSRuns well80.2 tok/s3510 ms33K
ReasoningSRuns well80.2 tok/s2852 ms33K
RAGSRuns well80.2 tok/s4388 ms33K

Quantization options

How Qwen 2.5 VL 72B (72B params) fits at each quantization level on NVIDIA GH200 96GB (96.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
28.1 GB
LowA83
Q3_K_S
3
35.3 GB
LowA84
NVFP4
4
40.3 GB
MediumS86
Q4_K_M
4
43.9 GB
MediumS86
Q5_K_M
5
51.8 GB
HighS88
Q6_K
6
59.0 GB
HighS88
Q8_0Best for your GPU
8
77.0 GB
Very HighS88
F16
16
147.6 GB
MaximumF0

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 NVIDIA GH200 96GB can run

ModelParamsGradeDecodeCapabilities
👁 Mistral
Devstral 2 123B Instruct		123BS47 tok/s
👁 Alibaba
Qwen 3.5 122B A10B		122BS130.3 tok/s
👁 Mistral
Mistral Small 4 119B		119BS141.2 tok/s
👁 OpenAI
GPT-OSS 120B		117BS49.4 tok/s
👁 Cohere
Command A 111B		111BS52.2 tok/s

Frequently asked questions

See all results for NVIDIA GH200 96GBSee all hardware for Qwen 2.5 VL 72B