← AI Hashrate

Can H200 141GB SXM5 run Qwen3-4B-Instruct-2507?

NVIDIA · 141 GB HBM3e · 4800 GB/s bandwidth · Alibaba · 4.0B · model ctx up to 256K

Yes — the H200 141GB SXM5 (141 GB HBM3e) can run Qwen3-4B-Instruct-2507. At Q4 with the default 8K context it needs ≈ 4.0 GB VRAM (weights 2.2 GB + KV cache 0.8 GB + 1 GB runtime overhead), which fits within 141 GB. Decode at Q4/8K: ≈ 763.6 tok/s (estimated, batch 1). FP16 (≈ 9.8 GB) also fits, at ≈ 210.0 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)
Q44K3.6 GBYes763.6 est.
Q48K default4.0 GBYes763.6 est.
Q432K6.4 GBYes763.6 est.
FP164K9.4 GBYes210.0 est.
FP168K default9.8 GBYes210.0 est.
FP1632K12.2 GBYes210.0 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
Q42.2 GB0.8 GB1 GB4.0 GB141 GB
FP168.0 GB0.8 GB1 GB9.8 GB141 GB

Other GPUs that run Qwen3-4B-Instruct-2507

All GPUs for Qwen3-4B-Instruct-2507 →

Other models for the H200 141GB SXM5

All models on the H200 141GB SXM5 →