General model by manjunathshiva · 28.58B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Qwen3.6 35B A3B tq3a tqTe g64 can run but will be tight at 79% of RAM. Consider a lower quantization or closing other apps.
— tok/s
Q4_K_M · 18.9 GB · Benchmark needed
Alternative: Q3_K_M (16.1 GB, ~154 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 32.4 GB | ~71 tok/s | ✗ |
| Q6_K | 25.2 GB | ~93 tok/s | ✗ |
| Q5_K_M | 21.8 GB | ~109 tok/s | ✗ |
| Q4_K_M Recommended | 18.9 GB | ~128 tok/s | ✓ |
| Q3_K_M | 16.1 GB | ~154 tok/s | ✓ |
| Q2_K | 12.9 GB | ~200 tok/s | ✓ |
Affiliate disclosure: the shop icons in this table are Amazon affiliate links. As an Amazon Associate, ModelPiper earns from qualifying purchases. Every fit rating, quantization and tok/s figure below is computed from the hardware specs and is not influenced by that.
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper free