NVIDIA · 24 GB GDDR6X · 1008 GB/s bandwidth ·
DeepSeek · 861.6B (active 49B) · MoE · model ctx up to 1000K
No — DeepSeek-V4-Pro at Q4 needs ≈ 479.78 GB even at 4K context, beyond the RTX 4090D 24GB (China)'s 24 GB GDDR6X. It would only run with heavy CPU/disk offload. FP16 needs ≈ 1734.0 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
479.78 GB
No
—
Q4
8K default
484.68 GB
No
—
Q4
32K
514.08 GB
No
—
FP16
4K
1729.1 GB
No
—
FP16
8K default
1734.0 GB
No
—
FP16
32K
1763.4 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).
VRAM breakdown at 8K context
Quant
Weights
KV cache
Overhead
Total needed
RTX 4090D 24GB (China) VRAM
Q4
473.88 GB
9.8 GB
1 GB
484.68 GB
24 GB
FP16
1723.2 GB
9.8 GB
1 GB
1734.0 GB
24 GB
Other GPUs that run DeepSeek-V4-Pro
No catalog GPU fully fits DeepSeek-V4-Pro at Q4/8K — see the model page for offload estimates.