Chat model by utter-project · 22.64B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
EuroLLM 22B Instruct 2512 can run but will be tight at 84% of RAM. Consider a lower quantization or closing other apps.
~9 tok/s
Q6_K · 20.1 GB · Estimated
Alternative: Q5_K_M (17.4 GB, ~11 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 25.8 GB | ~7 tok/s | ✗ |
| Q6_K Recommended | 20.1 GB | ~9 tok/s | ✓ |
| Q5_K_M | 17.4 GB | ~11 tok/s | ✓ |
| Q4_K_M | 15.1 GB | ~13 tok/s | ✓ |
| Q3_K_M | 12.9 GB | ~16 tok/s | ✓ |
| Q2_K | 10.4 GB | ~20 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