General model by bharatgenai · 17.15B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Param2 17B A2.4B Thinking fits comfortably in your 24 GB Mac using Q8_0 quantization, using 82% of your RAM.
— tok/s
Q8_0 · 19.6 GB · Benchmark needed
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 19.6 GB | ~67 tok/s | ✓ |
| Q6_K | 15.3 GB | ~88 tok/s | ✓ |
| Q5_K_M | 13.3 GB | ~104 tok/s | ✓ |
| Q4_K_M | 11.6 GB | ~122 tok/s | ✓ |
| Q3_K_M | 9.9 GB | ~147 tok/s | ✓ |
| Q2_K | 8.0 GB | ~191 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