Dense 2B-parameter open-weights language model from OpenBMB for on-device and edge deployment, Apache-2.0 licensed.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
MiniCPM5-2B is a dense 2B-parameter Transformer from OpenBMB, the second model in the MiniCPM5 series after MiniCPM5-1B. It scales up the same training recipe and is aimed at on-device, local and resource-constrained deployment. The Hugging Face card lists it with a Llama-style architecture in the transformers library, with English and Chinese language support.
According to the model card, it is the strongest open model in its comparison set of similar size and remains competitive with 4B-class models overall, with relative strengths in coding, mathematics, long-context understanding, tool use and agentic tasks. A YouTube reviewer reported that it beats Qwen3.5 4B on average across benchmarks and is about 5 GB in size. These are vendor and third-party benchmark claims and have not been independently verified here.
Weights are downloadable from Hugging Face under Apache-2.0, and the card links the training datasets (Ultra-FineWeb, UltraData-Math, UltraData-Code and SFT/RL sets) released by OpenBMB. An online demo is hosted on Hugging Face Spaces. It is text-only.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
2B dense small model that is state-of-the-art for its size, beating Qwen3.5 4B on average across benchmarks. About 5 GB; the training dataset is also released.
Closest neighbours by meaning, not just by category.
Model · OpenBMB
1B-parameter dense open-weights language model from OpenBMB for on-device use, with hybrid thinking and 128K context.
Model · OpenBMB
Small open-weights multimodal model from OpenBMB for image and video understanding on phones and edge devices.
Model · Liquid AI
Liquid AI's 24B-parameter mixture-of-experts LFM with 2B active parameters, built for fast on-device agents.
Model
Compact 1.7B open-weights text LLM for on-device use, with adjustable thinking levels and English/Chinese support.
Model · Alibaba
Small 0.8B-parameter open-weights language model in Alibaba's Qwen 3.5 family, aimed at lightweight and on-device use.
Model · Alibaba
Small 0.5B-parameter open-weights base language model from Alibaba's Qwen2.5 series, Apache 2.0 licensed.
