Multimodal model by wintercharm · 20.43B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Qwen3.5 122B A10B wMix48 fits comfortably in your 24 GB Mac using Q6_K quantization, using 76% of your RAM.
— tok/s
Q6_K · 18.2 GB · Benchmark needed
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 23.3 GB | ~99 tok/s | ✗ |
| Q6_K Recommended | 18.2 GB | ~130 tok/s | ✓ |
| Q5_K_M | 15.7 GB | ~153 tok/s | ✓ |
| Q4_K_M | 13.7 GB | ~179 tok/s | ✓ |
| Q3_K_M | 11.6 GB | ~216 tok/s | ✓ |
| Q2_K | 9.4 GB | ~280 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