Can Mistral Small 3.2 24B run on NVIDIA GH200 96GB?

YES — Runs Great

A82Great

Estimated from fit model

Mistral Small 3.2 24B needs ~27.9 GB VRAM. NVIDIA GH200 96GB has 96.0 GB. With Q4_K_M quantization, expect ~238 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: HighStack: BasicBottleneck: 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) — 27.9 GB, 237.9 tok/s, Runs well

27.9 GB required96.0 GB available

29% VRAM used

Fit status

Runs well

Decode

237.9 tok/s

TTFT

814 ms

Safe context

131K

Memory

27.9 GB / 96.0 GB

Memory breakdown

Weights14.6 GB

KV Cache2.4 GB

Runtime1.2 GB

Headroom9.6 GB

See how fast it feels

See how fast it feelsMistral Small 3.2 24B 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: 237.9 tok/s decode · 814ms TTFT (warm) · 595 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	A	Runs well	237.9 tok/s	444 ms	131K
Coding	A	Runs well	237.9 tok/s	814 ms	131K
Agentic Coding	A	Runs well	237.9 tok/s	1184 ms	131K
Reasoning	A	Runs well	237.9 tok/s	962 ms	131K
RAG	A	Runs well	237.9 tok/s	1480 ms	131K

Quantization options

How Mistral Small 3.2 24B (24B params) fits at each quantization level on NVIDIA GH200 96GB (96.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	9.4 GB	Low	A73
Q3_K_S	3	11.8 GB	Low	A74
NVFP4	4	13.4 GB	Medium	A74
Q4_K_M	4	14.6 GB	Medium	A74
Q5_K_M	5	17.3 GB	High	A74
Q6_K	6	19.7 GB	High	A75
Q8_0	8	25.7 GB	Very High	A75
F16Best for your GPU	16	49.2 GB	Maximum	A80

Get started

Copy-paste commands to run Mistral Small 3.2 24B on your machine.

Run

ollama run mistral-small3.2

Your hardware

More models your NVIDIA GH200 96GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	47 tok/s
Qwen3-Coder 30B A3B Instruct	30.5B	S	489.9 tok/s
Qwen 3.5 27B	27B	S	212.5 tok/s
Qwen 3.6 27B	27B	S	213.1 tok/s
Qwen 3.5 122B A10B	122B	S	130.3 tok/s

Frequently asked questions

Can NVIDIA GH200 96GB run Mistral Small 3.2 24B?

Yes, NVIDIA GH200 96GB can run Mistral Small 3.2 24B with a A grade (Runs well). Expected decode speed: 237.9 tok/s.

How much VRAM does Mistral Small 3.2 24B need?

Mistral Small 3.2 24B (24B parameters) requires approximately 27.9 GB of memory with Q4_K_M quantization.

What is the best quantization for Mistral Small 3.2 24B?

The recommended quantization for Mistral Small 3.2 24B is Q4_K_M, which balances quality and memory efficiency.

What speed will Mistral Small 3.2 24B run at on NVIDIA GH200 96GB?

On NVIDIA GH200 96GB, Mistral Small 3.2 24B achieves approximately 237.9 tokens per second decode speed with a time-to-first-token of 814ms using Q4_K_M quantization.

Can NVIDIA GH200 96GB run Mistral Small 3.2 24B for coding?

For coding workloads, Mistral Small 3.2 24B on NVIDIA GH200 96GB receives a A grade with 237.9 tok/s and 131K context.

What context window can Mistral Small 3.2 24B use on NVIDIA GH200 96GB?

On NVIDIA GH200 96GB, Mistral Small 3.2 24B can safely use up to 131K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

See all results for NVIDIA GH200 96GB See all hardware for Mistral Small 3.2 24B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/mistral-small-3.2-24b-on-gh200-96gb" 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

237.9 tok/s

444 ms

131K

Coding

Runs well

237.9 tok/s

814 ms

131K

Agentic Coding

Runs well

237.9 tok/s

1184 ms

131K

Reasoning

Runs well

237.9 tok/s

962 ms

131K

RAG

Runs well

237.9 tok/s

1480 ms

131K

Quantization options

How Mistral Small 3.2 24B (24B params) fits at each quantization level on NVIDIA GH200 96GB (96.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	9.4 GB	Low	A73
Q3_K_S	3	11.8 GB	Low	A74
NVFP4	4	13.4 GB	Medium	A74
Q4_K_M	4	14.6 GB	Medium	A74
Q5_K_M	5	17.3 GB	High	A74
Q6_K	6	19.7 GB	High	A75
Q8_0	8	25.7 GB	Very High	A75
F16Best for your GPU	16	49.2 GB	Maximum	A80

Model

Params

Grade

Decode

Capabilities

Devstral 2 123B Instruct

123B

47 tok/s

Qwen3-Coder 30B A3B Instruct

30.5B

489.9 tok/s

Qwen 3.5 27B

27B

212.5 tok/s

Qwen 3.6 27B

27B

213.1 tok/s

Qwen 3.5 122B A10B

122B

130.3 tok/s

Frequently asked questions

Can NVIDIA GH200 96GB run Mistral Small 3.2 24B?

Yes, NVIDIA GH200 96GB can run Mistral Small 3.2 24B with a A grade (Runs well). Expected decode speed: 237.9 tok/s.

How much VRAM does Mistral Small 3.2 24B need?

Mistral Small 3.2 24B (24B parameters) requires approximately 27.9 GB of memory with Q4_K_M quantization.

What is the best quantization for Mistral Small 3.2 24B?

The recommended quantization for Mistral Small 3.2 24B is Q4_K_M, which balances quality and memory efficiency.

What speed will Mistral Small 3.2 24B run at on NVIDIA GH200 96GB?

On NVIDIA GH200 96GB, Mistral Small 3.2 24B achieves approximately 237.9 tokens per second decode speed with a time-to-first-token of 814ms using Q4_K_M quantization.

Can NVIDIA GH200 96GB run Mistral Small 3.2 24B for coding?

For coding workloads, Mistral Small 3.2 24B on NVIDIA GH200 96GB receives a A grade with 237.9 tok/s and 131K context.

What context window can Mistral Small 3.2 24B use on NVIDIA GH200 96GB?

On NVIDIA GH200 96GB, Mistral Small 3.2 24B can safely use up to 131K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.