General model by hotdogs · 34.66B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Qwen35B Agent R2 can run but will be tight at 81% of RAM. Consider a lower quantization or closing other apps.
~10 tok/s
Q3_K_M · 19.4 GB · Estimated
Alternative: Q2_K (15.6 GB, ~13 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 39.2 GB | ~5 tok/s | ✗ |
| Q6_K | 30.5 GB | ~6 tok/s | ✗ |
| Q5_K_M | 26.3 GB | ~7 tok/s | ✗ |
| Q4_K_M | 22.9 GB | ~8 tok/s | ✗ |
| Q3_K_M Recommended | 19.4 GB | ~10 tok/s | ✓ |
| Q2_K | 15.6 GB | ~13 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