Will this model run on your hardware?
Can I run MiniCPM5-2B locally?
- 2.5B parameters
- context up to 128K
- licence: apache-2.0
- Weights: openbmb/MiniCPM5-2B · GGUF: bartowski/MiniCPM5-2B-GGUF
Open this page in a browser to check it against your own GPU or Mac: the tool detects your hardware locally and shows the best quantization that fits, the memory it needs and an estimated speed.
Quantizations and file sizes
| Quantization | GGUF file |
|---|---|
| Q8_0 | 2.7 GB |
| Q6_K | 2.1 GB |
| Q5_K_M | 1.9 GB |
| Q4_K_M | 1.6 GB |
| Q3_K_M | 1.2 GB |
| Q2_K | 1.0 GB |
Run it locally
ollama run hf.co/bartowski/MiniCPM5-2B-GGUF:Q4_K_M
llama serve -hf bartowski/MiniCPM5-2B-GGUF:Q4_K_M
LM Studio: open bartowski/MiniCPM5-2B-GGUF