General model by varjosoft · 34.13B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Qwen3.6 35B A3B TQ apex3 can run but will be tight at 80% of RAM. Consider a lower quantization or closing other apps.
— tok/s
Q3_K_M · 19.1 GB · Benchmark needed
Alternative: Q2_K (15.4 GB, ~168 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 38.6 GB | ~59 tok/s | ✗ |
| Q6_K | 30.0 GB | ~78 tok/s | ✗ |
| Q5_K_M | 25.9 GB | ~91 tok/s | ✗ |
| Q4_K_M | 22.5 GB | ~107 tok/s | ✗ |
| Q3_K_M Recommended | 19.1 GB | ~129 tok/s | ✓ |
| Q2_K | 15.4 GB | ~168 tok/s | ✓ |
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free