General model by vrizzo · 1.42B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
agri slm fits comfortably in your 24 GB Mac using Q8_0 quantization, using 9% of your RAM.
~113 tok/s
Q8_0 · 2.1 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 2.1 GB | ~113 tok/s | ✓ |
| Q6_K | 1.7 GB | ~149 tok/s | ✓ |
| Q5_K_M | 1.6 GB | ~175 tok/s | ✓ |
| Q4_K_M | 1.4 GB | ~205 tok/s | ✓ |
| Q3_K_M | 1.3 GB | ~248 tok/s | ✓ |
| Q2_K | 1.1 GB | ~321 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