Coding model by davidau · 52.96B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Qwen3 53B A3B 2507 THINKING TOTAL RECALL v2 MASTER CODER requires 23.6 GB which exceeds your available memory. You need a Mac with more RAM.
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 59.6 GB | ~24 tok/s | ✗ |
| Q6_K | 46.3 GB | ~32 tok/s | ✗ |
| Q5_K_M | 40.0 GB | ~38 tok/s | ✗ |
| Q4_K_M | 34.7 GB | ~44 tok/s | ✗ |
| Q3_K_M | 29.4 GB | ~53 tok/s | ✗ |
| Q2_K | 23.6 GB | ~69 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