General model by eleutherai · 0.21B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
pythia 160m deduped v0 fits comfortably in your 24 GB Mac using Q8_0 quantization, using 3% of your RAM.
~766 tok/s
Q8_0 · 0.7 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 0.7 GB | ~766 tok/s | ✓ |
| Q6_K | 0.7 GB | ~1,005 tok/s | ✓ |
| Q5_K_M | 0.7 GB | ~1,182 tok/s | ✓ |
| Q4_K_M | 0.6 GB | ~1,386 tok/s | ✓ |
| Q3_K_M | 0.6 GB | ~1,675 tok/s | ✓ |
| Q2_K | 0.6 GB | ~2,173 tok/s | ✓ |
GGUF Sources
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free