Reasoning model by healshsj · 1.08B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
MiniCPM5 1B Reasoning Agent Ultra fits comfortably in your 24 GB Mac using Q8_0 quantization, using 7% of your RAM.
~149 tok/s
Q8_0 · 1.7 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 1.7 GB | ~149 tok/s | ✓ |
| Q6_K | 1.4 GB | ~195 tok/s | ✓ |
| Q5_K_M | 1.3 GB | ~230 tok/s | ✓ |
| Q4_K_M | 1.2 GB | ~270 tok/s | ✓ |
| Q3_K_M | 1.1 GB | ~326 tok/s | ✓ |
| Q2_K | 1.0 GB | ~423 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