Coding model by mannix-ita · 26.66B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Qwen3.6 27B A3B Coder can run but will be tight at 85% of RAM. Consider a lower quantization or closing other apps.
— tok/s
Q5_K_M · 20.4 GB · Benchmark needed
Alternative: Q4_K_M (17.7 GB, ~107 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 30.2 GB | ~59 tok/s | ✗ |
| Q6_K | 23.6 GB | ~78 tok/s | ✗ |
| Q5_K_M Recommended | 20.4 GB | ~92 tok/s | ✓ |
| Q4_K_M | 17.7 GB | ~107 tok/s | ✓ |
| Q3_K_M | 15.0 GB | ~130 tok/s | ✓ |
| Q2_K | 12.1 GB | ~168 tok/s | ✓ |
GGUF Sources
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