Multimodal model by stepfun-ai · 0.72B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
GOT OCR2_0 fits comfortably in your 24 GB Mac using Q8_0 quantization, using 5% of your RAM.
~223 tok/s
Q8_0 · 1.3 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 1.3 GB | ~223 tok/s | ✓ |
| Q6_K | 1.1 GB | ~293 tok/s | ✓ |
| Q5_K_M | 1.0 GB | ~345 tok/s | ✓ |
| Q4_K_M | 1.0 GB | ~404 tok/s | ✓ |
| Q3_K_M | 0.9 GB | ~489 tok/s | ✓ |
| Q2_K | 0.8 GB | ~634 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