Chat model by opengvlab · 1.06B parameters
InternVL3_5 1B Instruct fits comfortably in your 24 GB Mac using Q8_0 quantization, using 7% of your RAM.
~152 tok/s
Q8_0 · 1.7 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 1.7 GB | ~152 tok/s | ✓ |
| Q6_K | 1.4 GB | ~199 tok/s | ✓ |
| Q5_K_M | 1.3 GB | ~234 tok/s | ✓ |
| Q4_K_M | 1.2 GB | ~275 tok/s | ✓ |
| Q3_K_M | 1.1 GB | ~332 tok/s | ✓ |
| Q2_K | 1.0 GB | ~431 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free