General model by beetle-humanscale · 0.19B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
beetle bilingual l2 50 sequential 0 100 b3 humanscale nld eng fits comfortably in your 24 GB Mac using Q8_0 quantization, using 3% of your RAM.
~846 tok/s
Q8_0 · 0.7 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 0.7 GB | ~846 tok/s | ✓ |
| Q6_K | 0.7 GB | ~1,111 tok/s | ✓ |
| Q5_K_M | 0.6 GB | ~1,307 tok/s | ✓ |
| Q4_K_M | 0.6 GB | ~1,532 tok/s | ✓ |
| Q3_K_M | 0.6 GB | ~1,851 tok/s | ✓ |
| Q2_K | 0.6 GB | ~2,402 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