← AI Hashrate

Can H100 80GB SXM5 run gemma-4-E4B-it?

NVIDIA · 80 GB HBM3 · 3350 GB/s bandwidth · Google · 8.0B · model ctx up to 128K

Yes — the H100 80GB SXM5 (80 GB HBM3) can run gemma-4-E4B-it. At Q4 with the default 8K context it needs ≈ 7.0 GB VRAM (weights 4.4 GB + KV cache 1.6 GB + 1 GB runtime overhead), which fits within 80 GB. Decode at Q4/8K: ≈ 266.5 tok/s (estimated, batch 1). FP16 (≈ 18.6 GB) also fits, at ≈ 73.3 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)
Q44K6.2 GBYes266.5 est.
Q48K default7.0 GBYes266.5 est.
Q432K11.8 GBYes266.5 est.
FP164K17.8 GBYes73.3 est.
FP168K default18.6 GBYes73.3 est.
FP1632K23.4 GBYes73.3 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
Q44.4 GB1.6 GB1 GB7.0 GB80 GB
FP1616.0 GB1.6 GB1 GB18.6 GB80 GB

Other GPUs that run gemma-4-E4B-it

All GPUs for gemma-4-E4B-it →

Other models for the H100 80GB SXM5

All models on the H100 80GB SXM5 →