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
Quant
Context
VRAM needed
Fits?
tok/s (decode)
Q4
4K
89.25 GB
No
229.1est.
Q4
8K default
90.55 GB
No
222.6est.
Q4
32K
98.36 GB
No
188.6est.
FP16
4K
318.5 GB
No
4.9est.
FP16
8K default
319.8 GB
No
4.9est.
FP16
32K
327.6 GB
No
—
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).