General model by cyankiwi · 14.74B parameters
Qwen3 Next 80B A3B Thinking AWQ 4bit fits comfortably in your 24 GB Mac using Q8_0 quantization, using 71% of your RAM.
~159 tok/s
Q8_0 · 16.9 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 16.9 GB | ~159 tok/s | ✓ |
| Q6_K | 13.3 GB | ~209 tok/s | ✓ |
| Q5_K_M | 11.5 GB | ~246 tok/s | ✓ |
| Q4_K_M | 10.0 GB | ~288 tok/s | ✓ |
| Q3_K_M | 8.5 GB | ~348 tok/s | ✓ |
| Q2_K | 6.9 GB | ~452 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free