Chat model by pretergeek · 8.99B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
OpenChat 3.5 0106_8.99B_40Layers Appended fits comfortably in your 24 GB Mac using Q8_0 quantization, using 44% of your RAM.
~18 tok/s
Q8_0 · 10.5 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 10.5 GB | ~18 tok/s | ✓ |
| Q6_K | 8.3 GB | ~23 tok/s | ✓ |
| Q5_K_M | 7.2 GB | ~28 tok/s | ✓ |
| Q4_K_M | 6.3 GB | ~32 tok/s | ✓ |
| Q3_K_M | 5.4 GB | ~39 tok/s | ✓ |
| Q2_K | 4.4 GB | ~51 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