DeepSeek V4 models
2 DeepSeek V4 models on Hugging Face, from 304.2B to 1650.5B parameters. At the precision each one is published in, the smallest needs about 564 GB of VRAM (DeepSeek-V4-Flash-0731, cheapest live fit: RTX PRO 6000) and the largest about 1128 GB (DeepSeek-V4-Pro-0813). The cheapest way to run DeepSeek-V4-Flash-0731 is $8.25/hr.
DeepSeek V4 models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| DeepSeek-V4-Flash-0731 | 304.2B | FP4 + FP8 Mixed | 564 GB | RTX PRO 6000 × 6 | $8.25/hr |
| DeepSeek-V4-Pro-0813 | 1650.5B | FP4 + FP8 Mixed | 1128 GB | No live fit | – |
VRAM is for the precision the model is published in, with the same overhead and an 8,192-token context assumed on every page; see the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
More from DeepSeek
- DeepSeek R1 (13 models)
- DeepSeek V3 (8 models)
- DeepSeek Coder (6 models)
- DeepSeek V2 (5 models)
- DeepSeek VL (4 models)
