DeepSeek Coder models
6 DeepSeek Coder models on Hugging Face, from 1.3B to 15.7B parameters. At the precision each one is published in, the smallest needs about 3.0 GB of VRAM (deepseek-coder-1.3b-instruct, cheapest live fit: RTX 5060 Ti) and the largest about 35.1 GB (DeepSeek-Coder-V2-Lite-Instruct, cheapest live fit: RTX A6000). The cheapest way to run deepseek-coder-1.3b-instruct is $0.110/hr.
DeepSeek Coder models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| deepseek-coder-1.3b-instruct | 1.3B | BF16 | 3.0 GB | RTX 5060 Ti | $0.110/hr |
| deepseek-coder-6.7b-base | 6.7B | BF16 | 15.1 GB | RTX 5060 Ti | $0.110/hr |
| deepseek-coder-6.7b-instruct | 6.7B | BF16 | 15.1 GB | RTX 5060 Ti | $0.110/hr |
| deepseek-coder-7b-instruct-v1.5 | 6.9B | BF16 | 15.4 GB | RTX 5060 Ti | $0.110/hr |
| DeepSeek-Coder-V2-Lite-Instruct | 15.7B | BF16 | 35.1 GB | RTX A6000 | $0.363/hr |
| DeepSeek-Coder-V2-Lite-Instruct-FP8 | 15.7B | F8_E4M3 | 17.6 GB | RTX 4000 SFF Ada | $0.198/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 V2 (5 models)
- DeepSeek VL (4 models)
