General model by jangq-ai · 25.6B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
MiniMax M2.7 JANG_3L can run but will be tight at 82% of RAM. Consider a lower quantization or closing other apps.
— tok/s
Q5_K_M · 19.6 GB · Benchmark needed
Alternative: Q4_K_M (17.0 GB, ~143 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 29.1 GB | ~79 tok/s | ✗ |
| Q6_K | 22.7 GB | ~103 tok/s | ✗ |
| Q5_K_M Recommended | 19.6 GB | ~122 tok/s | ✓ |
| Q4_K_M | 17.0 GB | ~143 tok/s | ✓ |
| Q3_K_M | 14.5 GB | ~172 tok/s | ✓ |
| Q2_K | 11.6 GB | ~224 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