Multimodal model by Meta · 12B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Llama Guard 4 12B fits comfortably in your 24 GB Mac using Q8_0 quantization, using 58% of your RAM.
— tok/s
Q8_0 · 13.9 GB · Benchmark needed
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 13.9 GB | ~123 tok/s | ✓ |
| Q6_K | 10.9 GB | ~161 tok/s | ✓ |
| Q5_K_M | 9.4 GB | ~189 tok/s | ✓ |
| Q4_K_M | 8.2 GB | ~222 tok/s | ✓ |
| Q3_K_M | 7.0 GB | ~268 tok/s | ✓ |
| Q2_K | 5.7 GB | ~348 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