Skip to content
can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA B200 (192GB) run Mistral Small 3.2 24B?

Mistral · Apache 2.0 · estimated for a 192.0 GB machine at 4K context.

Yes — it runs great.

Runs great

Best fit: Mistral Small 3.2 24B at FP16 · 47.2 GB weights · 92–139 tok/s on a NVIDIA B200 (192GB).

Arena Text Overall · style-controlled

1,356FP16 untested

mistral-small-2506 · published configuration reference · FP16 not tested

Arena Text Overall (style-controlled), exact published entry mistral-small-2506, 2026-10-08: reference rating 1,356.2. Published confidence bounds 1,351–1,361.5. 17,466 votes. Published mistral-small-2506 configuration reference. Reasoning mode is not disclosed by the Arena dataset. Tested precision, runtime and sampling settings are not disclosed in this dataset. Selected FP16 has not been measured by this Arena entry. No quantization quality adjustment is applied.

Snapshot published 2026-10-08 · snapshot imported 2026-10-11 UTC · validated last-good data · manual refresh

Arena leaderboard dataset · Arena / lmarena-ai, Arena Leaderboard Dataset (CC BY 4.0). Selected Text Overall style-controlled rows; field names adapted, ratings unchanged. · dataset CC BY 4.0 · revision e16f90232986

Total memory at 4K context
48.6 GB
Weights + KV cache + runtime overhead
Estimated generation
92–139 tok/s
Estimated first token
~0.5s

Every quantization on this machine

On small screens, each quant lists every metric below its name. On wider screens, scroll sideways for total memory, speed and fit. Keyboard: focus the table, then use the arrow keys. Quant names stay visible.

Mistral Small 3.2 24B quantizations on NVIDIA B200 (192GB), estimated at 4K context. Weights and total memory are shown separately.
QuantWeightsTotal memorySpeedFit
Q2_K8.9 GB10.4 GB230–345 tok/sRuns great
Q3_K_M11.5 GB12.9 GB209–314 tok/sRuns great
Q4_K_M14.3 GB15.8 GB190–285 tok/sRuns great
Q5_K_M16.8 GB18.2 GB176–264 tok/sRuns great
Q6_K19.4 GB20.8 GB164–245 tok/sRuns great
Q8_025.1 GB26.5 GB141–212 tok/sRuns great
FP1647.2 GB48.6 GB92–139 tok/sRuns great

Ran Mistral Small 3.2 24B on a NVIDIA B200 (192GB)? Add your real numbers →