General model by x-izhang · 3.25B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
libra v1.0 3b fits comfortably in your 24 GB Mac using Q8_0 quantization, using 17% of your RAM.
~49 tok/s
Q8_0 · 4.1 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 4.1 GB | ~49 tok/s | ✓ |
| Q6_K | 3.3 GB | ~65 tok/s | ✓ |
| Q5_K_M | 2.9 GB | ~76 tok/s | ✓ |
| Q4_K_M | 2.6 GB | ~90 tok/s | ✓ |
| Q3_K_M | 2.3 GB | ~108 tok/s | ✓ |
| Q2_K | 1.9 GB | ~140 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