Can Qwen 2.5 VL 72B run on B100 192GB?

YES — Runs Great

S90Excellent

Estimated from fit model

Qwen 2.5 VL 72B needs ~68.9 GB VRAM. B100 192GB has 192.0 GB. With Q4_K_M quantization, expect ~166 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: 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) — 68.9 GB, 166.4 tok/s, Runs well

68.9 GB required192.0 GB available

36% VRAM used

Fit status

Runs well

Decode

166.4 tok/s

TTFT

1164 ms

Safe context

33K

Memory

68.9 GB / 192.0 GB

Memory breakdown

Weights43.9 GB

KV Cache4.9 GB

Runtime0.9 GB

Headroom19.2 GB

See how fast it feels

See how fast it feelsQwen 2.5 VL 72B on B100 192GB
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: 166.4 tok/s decode · 1.2s TTFT (warm) · 416 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

Workload	Grade	Fit	Decode	TTFT	Context
Chat	S	Runs well	166.4 tok/s	635 ms	33K
Coding	S	Runs well	166.4 tok/s	1164 ms	33K
Agentic Coding	S	Runs well	166.4 tok/s	1692 ms	33K
Reasoning	S	Runs well	166.4 tok/s	1375 ms	33K
RAG	S	Runs well	166.4 tok/s	2115 ms	33K

Quantization options

How Qwen 2.5 VL 72B (72B params) fits at each quantization level on B100 192GB (192.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	28.1 GB	Low	A79
Q3_K_S	3	35.3 GB	Low	A80
NVFP4	4	40.3 GB	Medium	A80
Q4_K_M	4	43.9 GB	Medium	A81
Q5_K_M	5	51.8 GB	High	A82
Q6_K	6	59.0 GB	High	A83
Q8_0	8	77.0 GB	Very High	A85
F16Best for your GPU	16	147.6 GB	Maximum	S88

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 B100 192GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	97.4 tok/s
Qwen 3.5 122B A10B	122B	S	270.2 tok/s
DeepSeek V4 Flash	284B	S	144.8 tok/s
Mistral Small 4 119B	119B	S	292.9 tok/s
GPT-OSS 120B	117B	S	102.4 tok/s

Frequently asked questions

Can B100 192GB run Qwen 2.5 VL 72B?

Yes, B100 192GB can run Qwen 2.5 VL 72B with a S grade (Runs well). Expected decode speed: 166.4 tok/s.

How much VRAM does Qwen 2.5 VL 72B need?

Qwen 2.5 VL 72B (72B parameters) requires approximately 68.9 GB of memory with Q4_K_M quantization.

What is the best quantization for Qwen 2.5 VL 72B?

The recommended quantization for Qwen 2.5 VL 72B is Q4_K_M, which balances quality and memory efficiency.

What speed will Qwen 2.5 VL 72B run at on B100 192GB?

On B100 192GB, Qwen 2.5 VL 72B achieves approximately 166.4 tokens per second decode speed with a time-to-first-token of 1164ms using Q4_K_M quantization.

Can B100 192GB run Qwen 2.5 VL 72B for coding?

For coding workloads, Qwen 2.5 VL 72B on B100 192GB receives a S grade with 166.4 tok/s and 33K context.

What context window can Qwen 2.5 VL 72B use on B100 192GB?

On B100 192GB, Qwen 2.5 VL 72B can safely use up to 33K tokens of context. The model's official context limit is 33K, but available memory constrains the safe maximum.

See all results for B100 192GB See all hardware for Qwen 2.5 VL 72B

Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/qwen-2.5-vl-72b-on-b100-192gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview:

Workload

Grade

Fit

Decode

TTFT

Context

Chat

Runs well

166.4 tok/s

635 ms

33K

Coding

Runs well

166.4 tok/s

1164 ms

33K

Agentic Coding

Runs well

166.4 tok/s

1692 ms

33K

Reasoning

Runs well

166.4 tok/s

1375 ms

33K

RAG

Runs well

166.4 tok/s

2115 ms

33K

Quantization options

How Qwen 2.5 VL 72B (72B params) fits at each quantization level on B100 192GB (192.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	28.1 GB	Low	A79
Q3_K_S	3	35.3 GB	Low	A80
NVFP4	4	40.3 GB	Medium	A80
Q4_K_M	4	43.9 GB	Medium	A81
Q5_K_M	5	51.8 GB	High	A82
Q6_K	6	59.0 GB	High	A83
Q8_0	8	77.0 GB	Very High	A85
F16Best for your GPU	16	147.6 GB	Maximum	S88

Model

Params

Grade

Decode

Capabilities

Devstral 2 123B Instruct

123B

97.4 tok/s

Qwen 3.5 122B A10B

122B

270.2 tok/s

DeepSeek V4 Flash

284B

144.8 tok/s

Mistral Small 4 119B

119B

292.9 tok/s

GPT-OSS 120B

117B

102.4 tok/s

Frequently asked questions

Can B100 192GB run Qwen 2.5 VL 72B?

Yes, B100 192GB can run Qwen 2.5 VL 72B with a S grade (Runs well). Expected decode speed: 166.4 tok/s.

How much VRAM does Qwen 2.5 VL 72B need?

Qwen 2.5 VL 72B (72B parameters) requires approximately 68.9 GB of memory with Q4_K_M quantization.

What is the best quantization for Qwen 2.5 VL 72B?

The recommended quantization for Qwen 2.5 VL 72B is Q4_K_M, which balances quality and memory efficiency.

What speed will Qwen 2.5 VL 72B run at on B100 192GB?

On B100 192GB, Qwen 2.5 VL 72B achieves approximately 166.4 tokens per second decode speed with a time-to-first-token of 1164ms using Q4_K_M quantization.

Can B100 192GB run Qwen 2.5 VL 72B for coding?

For coding workloads, Qwen 2.5 VL 72B on B100 192GB receives a S grade with 166.4 tok/s and 33K context.

What context window can Qwen 2.5 VL 72B use on B100 192GB?

On B100 192GB, Qwen 2.5 VL 72B can safely use up to 33K tokens of context. The model's official context limit is 33K, but available memory constrains the safe maximum.