← AI Hashrate

Can H200 141GB SXM5 run Qwen3.5-9B?

NVIDIA · 141 GB HBM3e · 4800 GB/s bandwidth · Alibaba · 8.95B · model ctx up to 256K

Yes — the H200 141GB SXM5 (141 GB HBM3e) can run Qwen3.5-9B. At Q4 with the default 8K context it needs ≈ 7.71 GB VRAM (weights 4.92 GB + KV cache 1.79 GB + 1 GB runtime overhead), which fits within 141 GB. Decode at Q4/8K: ≈ 341.3 tok/s (estimated, batch 1). FP16 (≈ 20.69 GB) also fits, at ≈ 93.9 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)
Q44K6.82 GBYes341.3 est.
Q48K default7.71 GBYes341.3 est.
Q432K13.08 GBYes341.3 est.
FP164K19.79 GBYes93.9 est.
FP168K default20.69 GBYes93.9 est.
FP1632K26.06 GBYes93.9 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
Q44.92 GB1.79 GB1 GB7.71 GB141 GB
FP1617.9 GB1.79 GB1 GB20.69 GB141 GB

Other GPUs that run Qwen3.5-9B

All GPUs for Qwen3.5-9B →

Other models for the H200 141GB SXM5

All models on the H200 141GB SXM5 →