Chat model by alexwortega · 0.86B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
instruct_rugptlarge fits comfortably in your 24 GB Mac using Q8_0 quantization, using 6% of your RAM.
~187 tok/s
Q8_0 · 1.5 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 1.5 GB | ~187 tok/s | ✓ |
| Q6_K | 1.2 GB | ~245 tok/s | ✓ |
| Q5_K_M | 1.1 GB | ~289 tok/s | ✓ |
| Q4_K_M | 1.1 GB | ~339 tok/s | ✓ |
| Q3_K_M | 1.0 GB | ~409 tok/s | ✓ |
| Q2_K | 0.9 GB | ~531 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