General model by cyankiwi · 12.06B parameters
InternVL3_5 38B AWQ 4bit fits comfortably in your 24 GB Mac using Q8_0 quantization, using 58% of your RAM.
~13 tok/s
Q8_0 · 14.0 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 14.0 GB | ~13 tok/s | ✓ |
| Q6_K | 10.9 GB | ~18 tok/s | ✓ |
| Q5_K_M | 9.5 GB | ~21 tok/s | ✓ |
| Q4_K_M | 8.3 GB | ~24 tok/s | ✓ |
| Q3_K_M | 7.1 GB | ~29 tok/s | ✓ |
| Q2_K | 5.8 GB | ~38 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free