Chat model by cjvt · 11.77B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
GaMS3 12B Instruct fits comfortably in your 24 GB Mac using Q8_0 quantization, using 57% of your RAM.
~14 tok/s
Q8_0 · 13.6 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 13.6 GB | ~14 tok/s | ✓ |
| Q6_K | 10.7 GB | ~18 tok/s | ✓ |
| Q5_K_M | 9.3 GB | ~21 tok/s | ✓ |
| Q4_K_M | 8.1 GB | ~25 tok/s | ✓ |
| Q3_K_M | 6.9 GB | ~30 tok/s | ✓ |
| Q2_K | 5.6 GB | ~39 tok/s | ✓ |
GGUF Sources
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free