General model by final-bench · 1.88B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Darwin 2B Opus fits comfortably in your 24 GB Mac using Q8_0 quantization, using 11% of your RAM.
~86 tok/s
Q8_0 · 2.6 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 2.6 GB | ~86 tok/s | ✓ |
| Q6_K | 2.1 GB | ~112 tok/s | ✓ |
| Q5_K_M | 1.9 GB | ~132 tok/s | ✓ |
| Q4_K_M | 1.7 GB | ~155 tok/s | ✓ |
| Q3_K_M | 1.5 GB | ~187 tok/s | ✓ |
| Q2_K | 1.3 GB | ~243 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