Chat model by Meta · 8.03B parameters · Released 2024-07-18
Llama 3.1 8B Instruct fits comfortably in your 24 GB Mac using Q8_0 quantization, using 39% of your RAM.
~20 tok/s
Q8_0 · 9.5 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 9.5 GB | ~20 tok/s | ✓ |
| Q6_K | 7.5 GB | ~26 tok/s | ✓ |
| Q5_K_M | 6.5 GB | ~31 tok/s | ✓ |
| Q4_K_M | 5.7 GB | ~36 tok/s | ✓ |
| Q3_K_M | 4.9 GB | ~44 tok/s | ✓ |
| Q2_K | 4.0 GB | ~57 tok/s | ✓ |
GGUF Sources
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free