General model by quanttrio · 31.22B parameters
GLM 4.7 Flash AWQ can run but will be tight at 73% of RAM. Consider a lower quantization or closing other apps.
~11 tok/s
Q3_K_M · 17.5 GB
Alternative: Q2_K (14.1 GB, ~15 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 35.3 GB | ~5 tok/s | ✗ |
| Q6_K | 27.5 GB | ~7 tok/s | ✗ |
| Q5_K_M | 23.8 GB | ~8 tok/s | ✗ |
| Q4_K_M | 20.7 GB | ~9 tok/s | ✗ |
| Q3_K_M Recommended | 17.5 GB | ~11 tok/s | ✓ |
| Q2_K | 14.1 GB | ~15 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free