General model by obliteratus · 11.96B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Gemma 4 12B OBLITERATED fits comfortably in your 24 GB Mac using Q8_0 quantization, using 58% of your RAM.
~13 tok/s
Q8_0 · 13.8 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 13.8 GB | ~13 tok/s | ✓ |
| Q6_K | 10.9 GB | ~18 tok/s | ✓ |
| Q5_K_M | 9.4 GB | ~21 tok/s | ✓ |
| Q4_K_M | 8.2 GB | ~24 tok/s | ✓ |
| Q3_K_M | 7.0 GB | ~29 tok/s | ✓ |
| Q2_K | 5.7 GB | ~38 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