General model by ibm-granite · 6.67B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
granite 4.0 tiny preview fits comfortably in your 24 GB Mac using Q8_0 quantization, using 33% of your RAM.
— tok/s
Q8_0 · 7.9 GB · Benchmark needed
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 7.9 GB | ~170 tok/s | ✓ |
| Q6_K | 6.3 GB | ~223 tok/s | ✓ |
| Q5_K_M | 5.5 GB | ~262 tok/s | ✓ |
| Q4_K_M | 4.8 GB | ~307 tok/s | ✓ |
| Q3_K_M | 4.1 GB | ~371 tok/s | ✓ |
| Q2_K | 3.4 GB | ~482 tok/s | ✓ |
GGUF Sources
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free