General model by lennartkeller · 0.15B parameters · Released 2022-03-02
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
longformer gottbert base 8192 aw512 fits comfortably in your 24 GB Mac using Q8_0 quantization, using 3% of your RAM.
~1,072 tok/s
Q8_0 · 0.7 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 0.7 GB | ~1,072 tok/s | ✓ |
| Q6_K | 0.6 GB | ~1,407 tok/s | ✓ |
| Q5_K_M | 0.6 GB | ~1,655 tok/s | ✓ |
| Q4_K_M | 0.6 GB | ~1,941 tok/s | ✓ |
| Q3_K_M | 0.6 GB | ~2,345 tok/s | ✓ |
| Q2_K | 0.6 GB | ~3,042 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