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

Can I run this LLM?

Can a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) run Devstral Small 2 24B?

Mistral · See model card · estimated for a 144.0 GB machine at 4K context.

Yes — it runs great.

Runs great

Best fit: Devstral Small 2 24B at FP16 · 47.2 GB weights · 63–94 tok/s on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB).

Arena Text Overall · style-controlled

UnratedNo exact match

No reviewed exact Arena match

No reviewed exact model/configuration match in the Arena Text Overall style-controlled snapshot. No family or editorial score is substituted. Local quantization quality is unmeasured.

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
63–94 tok/s
Estimated first token
~1.1s

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.

Devstral Small 2 24B quantizations on NVIDIA GH200 Grace Hopper (144GB HBM + 480GB), estimated at 4K context. Weights and total memory are shown separately.
QuantWeightsTotal memorySpeedFit
Q2_K8.9 GB10.4 GB186–279 tok/sRuns great
Q3_K_M11.5 GB12.9 GB164–247 tok/sRuns great
Q4_K_M14.3 GB15.8 GB146–218 tok/sRuns great
Q5_K_M16.8 GB18.2 GB133–199 tok/sRuns great
Q6_K19.4 GB20.8 GB121–182 tok/sRuns great
Q8_025.1 GB26.5 GB102–152 tok/sRuns great
FP1647.2 GB48.6 GB63–94 tok/sRuns great

Ran Devstral Small 2 24B on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB)? Add your real numbers →