General model by ibm-granite · 2.98B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
granite vision 3.2 2b fits comfortably in your 24 GB Mac using Q8_0 quantization, using 16% of your RAM.
~54 tok/s
Q8_0 · 3.8 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 3.8 GB | ~54 tok/s | ✓ |
| Q6_K | 3.1 GB | ~71 tok/s | ✓ |
| Q5_K_M | 2.7 GB | ~83 tok/s | ✓ |
| Q4_K_M | 2.4 GB | ~98 tok/s | ✓ |
| Q3_K_M | 2.1 GB | ~118 tok/s | ✓ |
| Q2_K | 1.8 GB | ~153 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