← AI Hashrate

Can A100 80GB SXM4 run DeepSeek-V4-Flash?

NVIDIA · 80 GB HBM2e · 2039 GB/s bandwidth · DeepSeek · 158.1B (active 13B) · MoE · model ctx up to 1000K

No — DeepSeek-V4-Flash at Q4 needs ≈ 89.25 GB even at 4K context, beyond the A100 80GB SXM4's 80 GB HBM2e. It would only run with heavy CPU/disk offload. Decode at Q4/8K: ≈ 222.6 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 GBNo229.1 est.
Q48K default90.55 GBNo222.6 est.
Q432K98.36 GBNo188.6 est.
FP164K318.5 GBNo4.9 est.
FP168K default319.8 GBNo4.9 est.
FP1632K327.6 GBNo

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 neededA100 80GB SXM4 VRAM
Q486.95 GB2.6 GB1 GB90.55 GB80 GB
FP16316.2 GB2.6 GB1 GB319.8 GB80 GB

Other GPUs that run DeepSeek-V4-Flash

All GPUs for DeepSeek-V4-Flash →

Other models for the A100 80GB SXM4

All models on the A100 80GB SXM4 →