Chat model by ibnzterrell · 70.55B parameters
Meta Llama 3.3 70B Instruct AWQ INT4 requires 31.2 GB which exceeds your available memory. You need a Mac with more RAM.
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 79.2 GB | ~2 tok/s | ✗ |
| Q6_K | 61.6 GB | ~3 tok/s | ✗ |
| Q5_K_M | 53.1 GB | ~4 tok/s | ✗ |
| Q4_K_M | 46.0 GB | ~4 tok/s | ✗ |
| Q3_K_M | 39.0 GB | ~5 tok/s | ✗ |
| Q2_K | 31.2 GB | ~6 tok/s | ✗ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free