Reasoning model by kkhya · 0.5B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
llavaqwen2.5 0.5b finetune dyn col mask moe sparse 4e 2k sp0.9 r128_20260422_053621 fits comfortably in your 24 GB Mac using Q8_0 quantization, using 4% of your RAM.
~322 tok/s
Q8_0 · 1.1 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 1.1 GB | ~322 tok/s | ✓ |
| Q6_K | 0.9 GB | ~422 tok/s | ✓ |
| Q5_K_M | 0.9 GB | ~497 tok/s | ✓ |
| Q4_K_M | 0.8 GB | ~582 tok/s | ✓ |
| Q3_K_M | 0.8 GB | ~704 tok/s | ✓ |
| Q2_K | 0.7 GB | ~913 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