Chat model by Alibaba · 14.17B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Qwen1.5 14B Chat fits comfortably in your 24 GB Mac using Q8_0 quantization, using 68% of your RAM.
~11 tok/s
Q8_0 · 16.3 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 16.3 GB | ~11 tok/s | ✓ |
| Q6_K | 12.8 GB | ~15 tok/s | ✓ |
| Q5_K_M | 11.1 GB | ~18 tok/s | ✓ |
| Q4_K_M | 9.6 GB | ~21 tok/s | ✓ |
| Q3_K_M | 8.2 GB | ~25 tok/s | ✓ |
| Q2_K | 6.7 GB | ~32 tok/s | ✓ |
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free