DeepSeek VL models
4 DeepSeek VL models on Hugging Face, from 2.0B to 7.3B parameters. At the precision each one is published in, the smallest needs about 4.4 GB of VRAM (deepseek-vl-1.3b-chat, cheapest live fit: V100) and the largest about 16.4 GB (deepseek-vl-7b-chat, cheapest live fit: RTX A5000). The cheapest way to run deepseek-vl-1.3b-chat is $0.088/hr.
DeepSeek VL models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| deepseek-vl-1.3b-chat | 2.0B | F16 | 4.4 GB | V100 | $0.088/hr |
| deepseek-vl2-tiny | 3.4B | BF16 | 7.5 GB | RTX 5060 Ti | $0.110/hr |
| deepseek-vl2-tiny | 3.4B | BF16 | 7.5 GB | RTX 5060 Ti | $0.110/hr |
| deepseek-vl-7b-chat | 7.3B | F16 | 16.4 GB | RTX A5000 | $0.176/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 V2 (5 models)
