Code Llama models
3 Code Llama models on Hugging Face, from 6.7B to 33.7B parameters. At the precision each one is published in, the smallest needs about 15.1 GB of VRAM (CodeLlama-7b-hf, cheapest live fit: RTX 5060 Ti) and the largest about 75.4 GB (CodeLlama-34b-Instruct-hf, cheapest live fit: A100). The cheapest way to run CodeLlama-7b-hf is $0.110/hr.
Code Llama models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| CodeLlama-7b-hf | 6.7B | BF16 | 15.1 GB | RTX 5060 Ti | $0.110/hr |
| CodeLlama-7b-Instruct-hf | 6.7B | BF16 | 15.1 GB | RTX 5060 Ti | $0.110/hr |
| CodeLlama-34b-Instruct-hf | 33.7B | BF16 | 75.4 GB | A100 | $1.21/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.
