Model · multimodal model
WeVisOne-VL
WeVisOne-VL is a multimodal model from Tencent WeChat Vision, first covered on 4 November 2026. It is available as open weights you can download and run (licence: Apache 2.0). Its context window is up to 8,192 tokens (training), deploymen.
Last updated
Quick facts
- Who makes WeVisOne-VL?
- WeVisOne-VL is made by Tencent WeChat Vision.
- When was WeVisOne-VL released?
- The first report of WeVisOne-VL's release that Digest AI covered was published on 4 November 2026. Tencent releases WeVisOne-VL, a 2B/4B open vision model for detection, OCR and matting →
- What type of model is WeVisOne-VL?
- WeVisOne-VL is a multimodal model.
- Are WeVisOne-VL's weights open?
- Yes. WeVisOne-VL is released as open weights that can be downloaded and run, under the Apache 2.0 licence.
- What is WeVisOne-VL's context window?
- WeVisOne-VL's context window is up to 8,192 tokens (training), deploymen.
- Where is WeVisOne-VL available?
- WeVisOne-VL is available as open weights that can be downloaded and run. huggingface.co/tencent/WeVisOne-VL ↗
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
-
Tencent releases WeVisOne-VL, a 2B/4B open vision model for detection, OCR and matting
Tencent’s WeChat Vision team has open-sourced WeVisOne-VL, a vision-language model in 2B and 4B parameter sizes. It combines detection, object counting, referring, OCR, segmentation, and alpha matting into one model,…
1 sourceMarkTechPost
