General model by jangq-ai · 38.8B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Kimi K2.6 Small JANGTQ can run but will be tight at 72% of RAM. Consider a lower quantization or closing other apps.
— tok/s
Q2_K · 17.4 GB · Benchmark needed
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 43.8 GB | ~48 tok/s | ✗ |
| Q6_K | 34.1 GB | ~63 tok/s | ✗ |
| Q5_K_M | 29.4 GB | ~74 tok/s | ✗ |
| Q4_K_M | 25.5 GB | ~87 tok/s | ✗ |
| Q3_K_M | 21.7 GB | ~105 tok/s | ✗ |
| Q2_K Recommended | 17.4 GB | ~137 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