Chat model by redhatai · 108.64B parameters
Llama 4 Scout 17B 16E Instruct requires 47.8 GB which exceeds your available memory. You need a Mac with more RAM.
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 121.7 GB | ~14 tok/s | ✗ |
| Q6_K | 94.5 GB | ~18 tok/s | ✗ |
| Q5_K_M | 81.5 GB | ~21 tok/s | ✗ |
| Q4_K_M | 70.6 GB | ~24 tok/s | ✗ |
| Q3_K_M | 59.8 GB | ~30 tok/s | ✗ |
| Q2_K | 47.8 GB | ~38 tok/s | ✗ |
GGUF Sources
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free