General model by 0xvoid0000 · 4.21B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
zira researcher fits comfortably in your 24 GB Mac using Q8_0 quantization, using 22% of your RAM.
~38 tok/s
Q8_0 · 5.2 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 5.2 GB | ~38 tok/s | ✓ |
| Q6_K | 4.1 GB | ~50 tok/s | ✓ |
| Q5_K_M | 3.6 GB | ~59 tok/s | ✓ |
| Q4_K_M | 3.2 GB | ~69 tok/s | ✓ |
| Q3_K_M | 2.8 GB | ~84 tok/s | ✓ |
| Q2_K | 2.3 GB | ~108 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