Model · multimodal model
WeVisOne-VL-4B
WeVisOne-VL-4B is a multimodal model from Tencent, first covered on 23 October 2026. It is available as open weights you can download and run (licence: Apache License 2.0).
Last updated
Quick facts
- Who makes WeVisOne-VL-4B?
- WeVisOne-VL-4B is made by Tencent. Tencent news →
- When was WeVisOne-VL-4B released?
- The first report of WeVisOne-VL-4B's release that Digest AI covered was published on 23 October 2026.
- What type of model is WeVisOne-VL-4B?
- WeVisOne-VL-4B is a multimodal model.
- Are WeVisOne-VL-4B's weights open?
- Yes. WeVisOne-VL-4B is released as open weights that can be downloaded and run, under the Apache License 2.0.
- Where is WeVisOne-VL-4B available?
- WeVisOne-VL-4B is available as open weights that can be downloaded and run.
Taken from the coverage, not from our own testing. A question is left out when none of the reports we read gave the answer. All tracked models →
1 story about WeVisOne-VL-4B
-
Tencent releases WeVisOne-VL 4B vision-language model on Hugging Face
Tencent’s WeChat Vision team has published WeVisOne-VL-4B, a unified vision‑language model that combines object‑level tasks such as open‑vocabulary detection, referring localization, counting, pointing and OCR with…
1 source primary sourcehuggingface.co
Other models from Tencent