General model by pyoakum · 5.35B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
gpt oss 120b lora merged redux fits comfortably in your 24 GB Mac using Q8_0 quantization, using 27% of your RAM.
— tok/s
Q8_0 · 6.5 GB · Benchmark needed
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 6.5 GB | ~377 tok/s | ✓ |
| Q6_K | 5.1 GB | ~495 tok/s | ✓ |
| Q5_K_M | 4.5 GB | ~582 tok/s | ✓ |
| Q4_K_M | 4.0 GB | ~683 tok/s | ✓ |
| Q3_K_M | 3.4 GB | ~825 tok/s | ✓ |
| Q2_K | 2.8 GB | ~1,070 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