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

Can I run this LLM?

Can a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) run Mistral Small 4 119B (MoE)?

Mistral · Apache 2.0 · estimated for a 144.0 GB machine at 4K context.

Yes — it runs great.

Runs great

Best fit: Mistral Small 4 119B (MoE) at FP16 · 238.0 GB weights · 39–58 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
238.9 GB
Weights + KV cache + runtime overhead
Estimated generation
39–58 tok/s
Estimated first token
~0.3s

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 4 119B (MoE) quantizations on NVIDIA GH200 Grace Hopper (144GB HBM + 480GB), estimated at 4K context. Weights and total memory are shown separately.
QuantWeightsTotal memorySpeedFit
Q2_K40.2 GB41.1 GB298–447 tok/sRuns great
Q3_K_M54.4 GB55.3 GB280–420 tok/sRuns great
Q4_K_M73.8 GB74.7 GB259–388 tok/sRuns great
Q5_K_M89.2 GB90.1 GB244–366 tok/sRuns great
Q6_K99.4 GB100.3 GB235–353 tok/sRuns great
Q8_0126.5 GB127.4 GB215–322 tok/sRuns great
FP16238.0 GB238.9 GB39–58 tok/sRuns great

Ran Mistral Small 4 119B (MoE) on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB)? Add your real numbers →