← AI Hashrate

Can H200 141GB SXM5 run gemma-3-4b-it?

NVIDIA · 141 GB HBM3e · 4800 GB/s bandwidth · Google · 4.3B · model ctx up to 128K

Yes — the H200 141GB SXM5 (141 GB HBM3e) can run gemma-3-4b-it. At Q4 with the default 8K context it needs ≈ 4.15 GB VRAM (weights 2.37 GB + KV cache 0.78 GB + 1 GB runtime overhead), which fits within 141 GB. Decode at Q4/8K: ≈ 783.2 tok/s (estimated, batch 1). FP16 (≈ 10.38 GB) also fits, at ≈ 215.4 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)
Q44K3.76 GBYes783.2 est.
Q48K default4.15 GBYes783.2 est.
Q432K6.49 GBYes783.2 est.
FP164K9.99 GBYes215.4 est.
FP168K default10.38 GBYes215.4 est.
FP1632K12.72 GBYes215.4 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
Q42.37 GB0.78 GB1 GB4.15 GB141 GB
FP168.6 GB0.78 GB1 GB10.38 GB141 GB

Other GPUs that run gemma-3-4b-it

All GPUs for gemma-3-4b-it →

Other models for the H200 141GB SXM5

All models on the H200 141GB SXM5 →