General model by vandijklab · 28.41B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
C2S Scale Gemma 2 27B can run but will be tight at 78% of RAM. Consider a lower quantization or closing other apps.
~10 tok/s
Q4_K_M · 18.8 GB · Estimated
Alternative: Q3_K_M (16.0 GB, ~12 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 32.2 GB | ~6 tok/s | ✗ |
| Q6_K | 25.1 GB | ~7 tok/s | ✗ |
| Q5_K_M | 21.7 GB | ~9 tok/s | ✗ |
| Q4_K_M Recommended | 18.8 GB | ~10 tok/s | ✓ |
| Q3_K_M | 16.0 GB | ~12 tok/s | ✓ |
| Q2_K | 12.9 GB | ~16 tok/s | ✓ |
GGUF Sources
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free