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 | ✓ |
Affiliate disclosure: the shop icons in this table are Amazon affiliate links. As an Amazon Associate, ModelPiper earns from qualifying purchases. Every fit rating, quantization and tok/s figure below is computed from the hardware specs and is not influenced by that.
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper free