← AI Hashrate

Can H100 80GB SXM5 run gemma-4-31B-it?

NVIDIA · 80 GB HBM3 · 3350 GB/s bandwidth · Google · 30.7B · model ctx up to 256K

Yes — the H100 80GB SXM5 (80 GB HBM3) can run gemma-4-31B-it. At Q4 with the default 8K context it needs ≈ 24.03 GB VRAM (weights 16.89 GB + KV cache 6.14 GB + 1 GB runtime overhead), which fits within 80 GB. Decode at Q4/8K: ≈ 69.4 tok/s (estimated, batch 1). FP16 (≈ 68.54 GB) also fits, at ≈ 19.1 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)
Q44K20.96 GBYes69.4 est.
Q48K default24.03 GBYes69.4 est.
Q432K42.45 GBYes69.4 est.
FP164K65.47 GBYes19.1 est.
FP168K default68.54 GBYes19.1 est.
FP1632K86.96 GBNo46.2 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 neededH100 80GB SXM5 VRAM
Q416.89 GB6.14 GB1 GB24.03 GB80 GB
FP1661.4 GB6.14 GB1 GB68.54 GB80 GB

Other GPUs that run gemma-4-31B-it

All GPUs for gemma-4-31B-it →

Other models for the H100 80GB SXM5

All models on the H100 80GB SXM5 →