General model by eleutherai · 6.86B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
deep ignorance unfiltered cb lat fits comfortably in your 24 GB Mac using Q8_0 quantization, using 34% of your RAM.
~23 tok/s
Q8_0 · 8.2 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 8.2 GB | ~23 tok/s | ✓ |
| Q6_K | 6.4 GB | ~31 tok/s | ✓ |
| Q5_K_M | 5.6 GB | ~36 tok/s | ✓ |
| Q4_K_M | 4.9 GB | ~42 tok/s | ✓ |
| Q3_K_M | 4.2 GB | ~51 tok/s | ✓ |
| Q2_K | 3.5 GB | ~67 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