General model by cyankiwi · 32.14B parameters
GLM 4.7 Flash AWQ 4bit can run but will be tight at 75% of RAM. Consider a lower quantization or closing other apps.
~11 tok/s
Q3_K_M · 18.0 GB
Alternative: Q2_K (14.5 GB, ~14 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 36.4 GB | ~5 tok/s | ✗ |
| Q6_K | 28.3 GB | ~7 tok/s | ✗ |
| Q5_K_M | 24.5 GB | ~8 tok/s | ✗ |
| Q4_K_M | 21.2 GB | ~9 tok/s | ✗ |
| Q3_K_M Recommended | 18.0 GB | ~11 tok/s | ✓ |
| Q2_K | 14.5 GB | ~14 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free