Chat model by utter-project · 2.61B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
EuroMoE 2.6B A0.6B Instruct 2512 fits comfortably in your 24 GB Mac using Q8_0 quantization, using 14% of your RAM.
— tok/s
Q8_0 · 3.4 GB · Benchmark needed
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 3.4 GB | ~214 tok/s | ✓ |
| Q6_K | 2.8 GB | ~281 tok/s | ✓ |
| Q5_K_M | 2.4 GB | ~331 tok/s | ✓ |
| Q4_K_M | 2.2 GB | ~388 tok/s | ✓ |
| Q3_K_M | 1.9 GB | ~469 tok/s | ✓ |
| Q2_K | 1.6 GB | ~608 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