General model by jangq-ai · 25.36B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Gemma 4 26B A4B it JANG_4M can run but will be tight at 81% of RAM. Consider a lower quantization or closing other apps.
— tok/s
Q5_K_M · 19.4 GB · Benchmark needed
Alternative: Q4_K_M (16.9 GB, ~105 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 28.8 GB | ~58 tok/s | ✗ |
| Q6_K | 22.4 GB | ~76 tok/s | ✗ |
| Q5_K_M Recommended | 19.4 GB | ~90 tok/s | ✓ |
| Q4_K_M | 16.9 GB | ~105 tok/s | ✓ |
| Q3_K_M | 14.3 GB | ~127 tok/s | ✓ |
| Q2_K | 11.5 GB | ~165 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