General model by Meta · 405.85B parameters
Llama 3.1 405B requires 177.3 GB which exceeds your available memory. You need a Mac with more RAM.
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 453.2 GB | ~0 tok/s | ✗ |
| Q6_K | 351.8 GB | ~1 tok/s | ✗ |
| Q5_K_M | 303.1 GB | ~1 tok/s | ✗ |
| Q4_K_M | 262.5 GB | ~1 tok/s | ✗ |
| Q3_K_M | 221.9 GB | ~1 tok/s | ✗ |
| Q2_K | 177.3 GB | ~1 tok/s | ✗ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free