General model by hweri · 0.07B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
pythia 70m deduped cleansharegpt fits comfortably in your 24 GB Mac using Q8_0 quantization, using 2% of your RAM.
~2,297 tok/s
Q8_0 · 0.6 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 0.6 GB | ~2,297 tok/s | ✓ |
| Q6_K | 0.6 GB | ~3,015 tok/s | ✓ |
| Q5_K_M | 0.6 GB | ~3,547 tok/s | ✓ |
| Q4_K_M | 0.5 GB | ~4,159 tok/s | ✓ |
| Q3_K_M | 0.5 GB | ~5,025 tok/s | ✓ |
| Q2_K | 0.5 GB | ~6,519 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