← AI Hashrate

Can H200 141GB SXM5 run DeepSeek-V4-Flash?

NVIDIA · 141 GB HBM3e · 4800 GB/s bandwidth · DeepSeek · 158.1B (active 13B) · MoE · model ctx up to 1000K

Yes — the H200 141GB SXM5 (141 GB HBM3e) can run DeepSeek-V4-Flash. At Q4 with the default 8K context it needs ≈ 90.55 GB VRAM (weights 86.95 GB + KV cache 2.6 GB + 1 GB runtime overhead), which fits within 141 GB. Decode at Q4/8K: ≈ 235.0 tok/s (estimated, batch 1). FP16 needs ≈ 319.8 GB — does not fit on this card. 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)
Q44K89.25 GBYes235.0 est.
Q48K default90.55 GBYes235.0 est.
Q432K98.36 GBYes235.0 est.
FP164K318.5 GBNo36.2 est.
FP168K default319.8 GBNo35.9 est.
FP1632K327.6 GBNo34.2 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
Q486.95 GB2.6 GB1 GB90.55 GB141 GB
FP16316.2 GB2.6 GB1 GB319.8 GB141 GB

Other GPUs that run DeepSeek-V4-Flash

All GPUs for DeepSeek-V4-Flash →

Other models for the H200 141GB SXM5

All models on the H200 141GB SXM5 →