General model by ibm-granite · 6.94B parameters · Released 2025-09-16
granite 4.0 h tiny fits comfortably in your 24 GB Mac using Q8_0 quantization, using 34% of your RAM.
~167 tok/s
Q8_0 · 8.2 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 8.2 GB | ~167 tok/s | ✓ |
| Q6_K | 6.5 GB | ~219 tok/s | ✓ |
| Q5_K_M | 5.7 GB | ~257 tok/s | ✓ |
| Q4_K_M | 5.0 GB | ~302 tok/s | ✓ |
| Q3_K_M | 4.3 GB | ~365 tok/s | ✓ |
| Q2_K | 3.5 GB | ~473 tok/s | ✓ |
GGUF Sources
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free