Method | Bits | 7B | 13B | 30B | 65B | 8x7B |
---|---|---|---|---|---|---|
Full | 16 | 160GB | 320GB | 600GB | 1200GB | 900GB |
Freeze | 16 | 20GB | 40GB | 120GB | 240GB | 200GB |
LoRA | 16 | 16GB | 32GB | 80GB | 160GB | 120GB |
QLoRA | 8 | 10GB | 16GB | 40GB | 80GB | 80GB |
QLoRA | 4 | 6GB | 12GB | 24GB | 48GB | 32GB |
Created
January 23, 2024 07:57
-
-
Save bigsnarfdude/e169657fe0dad5d07f45a1baf994be65 to your computer and use it in GitHub Desktop.
table_vram.md
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Mixtral instruct Q5_K_M gguf
Total Tokens: 540, Time: 47.31s. Tokens per second 10.00