General model by farbodtavakkoli · 1.77B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
OTel LLM 20B IT fits comfortably in your 24 GB Mac using Q8_0 quantization, using 10% of your RAM.
— tok/s
Q8_0 · 2.5 GB · Benchmark needed
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 2.5 GB | ~537 tok/s | ✓ |
| Q6_K | 2.0 GB | ~705 tok/s | ✓ |
| Q5_K_M | 1.8 GB | ~830 tok/s | ✓ |
| Q4_K_M | 1.6 GB | ~973 tok/s | ✓ |
| Q3_K_M | 1.5 GB | ~1,175 tok/s | ✓ |
| Q2_K | 1.3 GB | ~1,525 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