General model by moonshotai · 15.96B parameters
Moonlight 16B A3B fits comfortably in your 24 GB Mac using Q8_0 quantization, using 76% of your RAM.
~139 tok/s
Q8_0 · 18.3 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 18.3 GB | ~139 tok/s | ✓ |
| Q6_K | 14.3 GB | ~183 tok/s | ✓ |
| Q5_K_M | 12.4 GB | ~215 tok/s | ✓ |
| Q4_K_M | 10.8 GB | ~252 tok/s | ✓ |
| Q3_K_M | 9.2 GB | ~305 tok/s | ✓ |
| Q2_K | 7.5 GB | ~396 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free