General model by inclusionai · 16.26B parameters
LLaDA2.1 mini fits comfortably in your 24 GB Mac using Q8_0 quantization, using 78% of your RAM.
~124 tok/s
Q8_0 · 18.6 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 18.6 GB | ~124 tok/s | ✓ |
| Q6_K | 14.6 GB | ~163 tok/s | ✓ |
| Q5_K_M | 12.6 GB | ~192 tok/s | ✓ |
| Q4_K_M | 11.0 GB | ~225 tok/s | ✓ |
| Q3_K_M | 9.4 GB | ~272 tok/s | ✓ |
| Q2_K | 7.6 GB | ~352 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free