General model by ibm-granite · 1.46B parameters
granite 4.0 h 1b fits comfortably in your 24 GB Mac using Q8_0 quantization, using 9% of your RAM.
~110 tok/s
Q8_0 · 2.1 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 2.1 GB | ~110 tok/s | ✓ |
| Q6_K | 1.8 GB | ~145 tok/s | ✓ |
| Q5_K_M | 1.6 GB | ~170 tok/s | ✓ |
| Q4_K_M | 1.4 GB | ~199 tok/s | ✓ |
| Q3_K_M | 1.3 GB | ~241 tok/s | ✓ |
| Q2_K | 1.1 GB | ~313 tok/s | ✓ |
GGUF Sources
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free