MiniCPM5 (2B, Q4)
OpenBMB's MiniCPM5 at 2B parameters: a dense Llama-architecture deep-thinking model post-trained with RL and on-policy distillation for tool use, coding and long context, with a 128K context window. Sized for phones with 4 GB or more.
| At a glance | |
|---|---|
| Made by | OpenBMB |
| Download size | 1.6 GB |
| Parameters | 2B |
| Quantization | Q4_K_M |
| Context window | 131K tokens |
| Uses tools | Yes |
| Best for | Everyday work |
| Runs on | llama.cpp, MLX |
| License | Apache-2.0 |
| Added to the catalog | 2026-09-27 |
Gezel downloads this model the first time a gezel needs it, checks the file against its published hash, and applies tuned settings for it.