Chat model by redhatai · 401.65B parameters
Llama 4 Maverick 17B 128E Instruct FP8 requires 175.4 GB which exceeds your available memory. You need a Mac with more RAM.
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 448.6 GB | ~4 tok/s | ✗ |
| Q6_K | 348.1 GB | ~5 tok/s | ✗ |
| Q5_K_M | 299.9 GB | ~6 tok/s | ✗ |
| Q4_K_M | 259.8 GB | ~7 tok/s | ✗ |
| Q3_K_M | 219.6 GB | ~8 tok/s | ✗ |
| Q2_K | 175.4 GB | ~10 tok/s | ✗ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free