← AI Hashrate

Can L40S 48GB run gemma-4-E2B-it?

NVIDIA · 48 GB GDDR6 · 864 GB/s bandwidth · Google · 5.1B · model ctx up to 128K

Yes — the L40S 48GB (48 GB GDDR6) can run gemma-4-E2B-it. At Q4 with the default 8K context it needs ≈ 4.83 GB VRAM (weights 2.81 GB + KV cache 1.02 GB + 1 GB runtime overhead), which fits within 48 GB. Decode at Q4/8K: ≈ 107.8 tok/s (estimated, batch 1). FP16 (≈ 12.22 GB) also fits, at ≈ 29.6 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)
Q44K4.32 GBYes107.8 est.
Q48K default4.83 GBYes107.8 est.
Q432K7.88 GBYes107.8 est.
FP164K11.71 GBYes29.6 est.
FP168K default12.22 GBYes29.6 est.
FP1632K15.28 GBYes29.6 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 neededL40S 48GB VRAM
Q42.81 GB1.02 GB1 GB4.83 GB48 GB
FP1610.2 GB1.02 GB1 GB12.22 GB48 GB

Other GPUs that run gemma-4-E2B-it

All GPUs for gemma-4-E2B-it →

Other models for the L40S 48GB

All models on the L40S 48GB →