General model by lmstudio-community · 111.93B parameters
Qwen3.5 397B A17B requires 69.4 GB which exceeds your available memory. You need a Mac with more RAM.
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| mlx-8bit | 119.8 GB | ~19 tok/s | ✗ |
| mlx-4bit | 69.4 GB | ~34 tok/s | ✗ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free