General model by apolo13x · 6.38B parameters
Qwen3.5 35B A3B quantized.w4a16 fits comfortably in your 24 GB Mac using Q8_0 quantization, using 32% of your RAM.
~316 tok/s
Q8_0 · 7.6 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 7.6 GB | ~316 tok/s | ✓ |
| Q6_K | 6.0 GB | ~415 tok/s | ✓ |
| Q5_K_M | 5.3 GB | ~488 tok/s | ✓ |
| Q4_K_M | 4.6 GB | ~573 tok/s | ✓ |
| Q3_K_M | 4.0 GB | ~692 tok/s | ✓ |
| Q2_K | 3.3 GB | ~897 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free