General model by Google · 27.43B parameters · Released 2025-03-01
gemma 3 27b it can run but will be tight at 76% of RAM. Consider a lower quantization or closing other apps.
~11 tok/s
Q4_K_M · 18.2 GB
Alternative: Q3_K_M (15.5 GB, ~13 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 31.1 GB | ~6 tok/s | ✗ |
| Q6_K | 24.2 GB | ~8 tok/s | ✗ |
| Q5_K_M | 21.0 GB | ~9 tok/s | ✗ |
| Q4_K_M Recommended | 18.2 GB | ~11 tok/s | ✓ |
| Q3_K_M | 15.5 GB | ~13 tok/s | ✓ |
| Q2_K | 12.4 GB | ~17 tok/s | ✓ |
GGUF Sources
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free