← AI Hashrate

Can Gaudi 3 128GB run DeepSeek-V4-Flash?

Intel · 128 GB HBM2e · 3276 GB/s bandwidth · DeepSeek · 158.1B (active 13B) · MoE · model ctx up to 1000K

Yes — the Gaudi 3 128GB (128 GB HBM2e) can run DeepSeek-V4-Flash. At Q4 with the default 8K context it needs ≈ 90.55 GB VRAM (weights 86.95 GB + KV cache 2.6 GB + 1 GB runtime overhead), which fits within 128 GB. Decode at Q4/8K: ≈ 160.4 tok/s (estimated, batch 1). FP16 needs ≈ 319.8 GB — does not fit on this card. 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)
Q44K89.25 GBYes160.4 est.
Q48K default90.55 GBYes160.4 est.
Q432K98.36 GBYes160.4 est.
FP164K318.5 GBNo20.4 est.
FP168K default319.8 GBNo20.2 est.
FP1632K327.6 GBNo19.2 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 neededGaudi 3 128GB VRAM
Q486.95 GB2.6 GB1 GB90.55 GB128 GB
FP16316.2 GB2.6 GB1 GB319.8 GB128 GB

Other GPUs that run DeepSeek-V4-Flash

All GPUs for DeepSeek-V4-Flash →

Other models for the Gaudi 3 128GB

All models on the Gaudi 3 128GB →