← AI Hashrate

Can H200 141GB SXM5 run Magistral-Small-2509?

NVIDIA · 141 GB HBM3e · 4800 GB/s bandwidth · Mistral · 24.0B · model ctx up to 128K

Yes — the H200 141GB SXM5 (141 GB HBM3e) can run Magistral-Small-2509. At Q4 with the default 8K context it needs ≈ 19.0 GB VRAM (weights 13.2 GB + KV cache 4.8 GB + 1 GB runtime overhead), which fits within 141 GB. Decode at Q4/8K: ≈ 127.3 tok/s (estimated, batch 1). FP16 (≈ 53.8 GB) also fits, at ≈ 35.0 tok/s (estimated). Estimates come from memory-bandwidth math; rows tagged measured override estimates. Relative ranking is more reliable than absolute tok/s. Methodology.

Fit & speed by quant and context

QuantContextVRAM neededFits?tok/s (decode)
Q44K16.6 GBYes127.3 est.
Q48K default19.0 GBYes127.3 est.
Q432K33.4 GBYes127.3 est.
FP164K51.4 GBYes35.0 est.
FP168K default53.8 GBYes35.0 est.
FP1632K68.2 GBYes35.0 est.

Fits = weights + KV(ctx) + 1 GB overhead ≤ 95% of VRAM. Measured anchors are context-agnostic; the fit verdict is recomputed per context. A missing tok/s means the model is far beyond this card (offload-only territory).

VRAM breakdown at 8K context

QuantWeightsKV cacheOverheadTotal neededH200 141GB SXM5 VRAM
Q413.2 GB4.8 GB1 GB19.0 GB141 GB
FP1648.0 GB4.8 GB1 GB53.8 GB141 GB

Other GPUs that run Magistral-Small-2509

All GPUs for Magistral-Small-2509 →

Other models for the H200 141GB SXM5

All models on the H200 141GB SXM5 →