Chat model by cmarkea · 0.56B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
bloomz 560m sft chat fits comfortably in your 24 GB Mac using Q8_0 quantization, using 5% of your RAM.
~287 tok/s
Q8_0 · 1.1 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 1.1 GB | ~287 tok/s | ✓ |
| Q6_K | 1.0 GB | ~377 tok/s | ✓ |
| Q5_K_M | 0.9 GB | ~443 tok/s | ✓ |
| Q4_K_M | 0.9 GB | ~520 tok/s | ✓ |
| Q3_K_M | 0.8 GB | ~628 tok/s | ✓ |
| Q2_K | 0.7 GB | ~815 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