General model by varjosoft · 15.79B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Qwen3.6 35B A3B TQ apex fits comfortably in your 24 GB Mac using Q8_0 quantization, using 75% of your RAM.
— tok/s
Q8_0 · 18.1 GB · Benchmark needed
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 18.1 GB | ~128 tok/s | ✓ |
| Q6_K | 14.2 GB | ~168 tok/s | ✓ |
| Q5_K_M | 12.3 GB | ~197 tok/s | ✓ |
| Q4_K_M | 10.7 GB | ~231 tok/s | ✓ |
| Q3_K_M | 9.1 GB | ~280 tok/s | ✓ |
| Q2_K | 7.4 GB | ~363 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