← AI Hashrate

Can Gaudi 3 128GB run gemma-3-1b-it?

Intel · 128 GB HBM2e · 3276 GB/s bandwidth · Google · 1.0B · model ctx up to 32K

Yes — the Gaudi 3 128GB (128 GB HBM2e) can run gemma-3-1b-it. At Q4 with the default 8K context it needs ≈ 1.75 GB VRAM (weights 0.55 GB + KV cache 0.2 GB + 1 GB runtime overhead), which fits within 128 GB. Decode at Q4/8K: ≈ 2084.7 tok/s (estimated, batch 1). FP16 (≈ 3.2 GB) also fits, at ≈ 573.3 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)
Q44K1.65 GBYes2084.7 est.
Q48K default1.75 GBYes2084.7 est.
Q432K2.35 GBYes2084.7 est.
FP164K3.1 GBYes573.3 est.
FP168K default3.2 GBYes573.3 est.
FP1632K3.8 GBYes573.3 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 neededGaudi 3 128GB VRAM
Q40.55 GB0.2 GB1 GB1.75 GB128 GB
FP162.0 GB0.2 GB1 GB3.2 GB128 GB

Other GPUs that run gemma-3-1b-it

All GPUs for gemma-3-1b-it →

Other models for the Gaudi 3 128GB

All models on the Gaudi 3 128GB →