DeepSeek V2 models
5 DeepSeek V2 models on Hugging Face, from 15.7B to 235.7B parameters. At the precision each one is published in, the smallest needs about 35.1 GB of VRAM (DeepSeek-V2-Lite, cheapest live fit: RTX A6000) and the largest about 527 GB (DeepSeek-V2, cheapest live fit: RTX PRO 6000). The cheapest way to run DeepSeek-V2-Lite is $0.363/hr.
DeepSeek V2 models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| DeepSeek-V2-Lite | 15.7B | BF16 | 35.1 GB | RTX A6000 | $0.363/hr |
| DeepSeek-V2-Lite-Chat | 15.7B | BF16 | 35.1 GB | RTX A6000 | $0.363/hr |
| DeepSeek-V2 | 235.7B | BF16 | 527 GB | RTX PRO 6000 × 6 | $8.25/hr |
| DeepSeek-V2-Chat | 235.7B | BF16 | 527 GB | RTX PRO 6000 × 6 | $8.25/hr |
| DeepSeek-V2.5-1210-FP8 | 235.7B | F8_E4M3 | 263 GB | RTX 4090 × 6 | $2.64/hr |
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 VL (4 models)
