Chat model by mtgv · 1.02B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
MobileLLaMA 1.4B Chat fits comfortably in your 24 GB Mac using Q8_0 quantization, using 7% of your RAM.
~158 tok/s
Q8_0 · 1.6 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 1.6 GB | ~158 tok/s | ✓ |
| Q6_K | 1.4 GB | ~207 tok/s | ✓ |
| Q5_K_M | 1.3 GB | ~243 tok/s | ✓ |
| Q4_K_M | 1.2 GB | ~285 tok/s | ✓ |
| Q3_K_M | 1.1 GB | ~345 tok/s | ✓ |
| Q2_K | 0.9 GB | ~447 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