General model by opengvlab · 3.71B parameters
InternVL2_5 4B MPO fits comfortably in your 24 GB Mac using Q8_0 quantization, using 19% of your RAM.
~43 tok/s
Q8_0 · 4.6 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 4.6 GB | ~43 tok/s | ✓ |
| Q6_K | 3.7 GB | ~57 tok/s | ✓ |
| Q5_K_M | 3.3 GB | ~67 tok/s | ✓ |
| Q4_K_M | 2.9 GB | ~78 tok/s | ✓ |
| Q3_K_M | 2.5 GB | ~95 tok/s | ✓ |
| Q2_K | 2.1 GB | ~123 tok/s | ✓ |
GGUF Sources
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free