General model by p-e-w · 22.11B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro, Mac mini M5 Pro
gpt oss 20b heretic ara v4 fits comfortably in your 24 GB Mac using Q6_K quantization, using 82% of your RAM.
Specifications
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 25.2 GB | ~43 tok/s | ✗ |
| Q6_K Recommended | 19.6 GB | ~57 tok/s | ✓ |
| Q5_K_M | 17.0 GB | ~67 tok/s | ✓ |
| Q4_K_M | 14.8 GB | ~78 tok/s | ✓ |
| Q3_K_M | 12.6 GB | ~94 tok/s | ✓ |
| Q2_K | 10.1 GB | ~122 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