← AI Hashrate

Can Gaudi 3 128GB run gemma-4-12b-it?

Intel · 128 GB HBM2e · 3276 GB/s bandwidth · Google · 11.95B · model ctx up to 256K

Yes — the Gaudi 3 128GB (128 GB HBM2e) can run gemma-4-12b-it. At Q4 with the default 8K context it needs ≈ 9.96 GB VRAM (weights 6.57 GB + KV cache 2.39 GB + 1 GB runtime overhead), which fits within 128 GB. Decode at Q4/8K: ≈ 174.5 tok/s (estimated, batch 1). FP16 (≈ 27.29 GB) also fits, at ≈ 48.0 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)
Q44K8.77 GBYes174.5 est.
Q48K default9.96 GBYes174.5 est.
Q432K17.13 GBYes174.5 est.
FP164K26.09 GBYes48.0 est.
FP168K default27.29 GBYes48.0 est.
FP1632K34.46 GBYes48.0 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
Q46.57 GB2.39 GB1 GB9.96 GB128 GB
FP1623.9 GB2.39 GB1 GB27.29 GB128 GB

Other GPUs that run gemma-4-12b-it

All GPUs for gemma-4-12b-it →

Other models for the Gaudi 3 128GB

All models on the Gaudi 3 128GB →