WeVisOne-VL-2B: Neuheiten, nötige Hardware, so nutzt du es kostenlos

Tencent released WeVisOne-VL-2B, a 2.4 billion-parameter vision-language model that handles objects and pixels in one go. It runs on a modest RTX 4060 with just 4 GB memory.

WeVisOne-VL-2B is a vision-language model from Tencent's WeChat Vision team. According to the model card, it builds on Qwen3-VL and adds a lightweight 9.5 million-parameter pixel decoder. The model can predict bounding boxes, points, and full-resolution alpha mattes directly from images, using special coordinate and instance tokens.

The new part is a dedicated pixel decoder that combines a visual feature adapter, a box-guided query decoder, and an instance-conditioned dense prediction head. It produces dense outputs like segmentation and matting without a separate processing stage. The model also returns None when a queried target is absent, simplifying downstream handling.

According to the model card, the model excels at open-vocabulary object detection, referring localization, counting, OCR, segmentation, and promptable alpha matting. However, fine alpha boundaries can be affected by image resolution, severe occlusion, complex transparency, and how prompts are phrased. It is designed for single-turn image perception; video grids are rejected.

The release is aimed at research on visual grounding, referring localization, pointing, counting, OCR localization, segmentation, and image matting. Because it fits in the memory of an RTX 4060 at 4 GB, hobbyists with a modest GPU can also experiment. No free API is available yet, but the weights can be downloaded from Hugging Face.

Was brauchst du, um es zu Hause auszuführen? Bei 4 Bit belegt es etwa 4 Gigabyte Speicher. Der kleinste Heimrechner, der es komplett fasst, ist ein RTX 4060. Auf einem RTX 3060 12 GB mit 32 Gigabyte RAM schreibt es etwa 105 Tokens pro Sekunde. Auf einem RTX 4090 mit 64 Gigabyte RAM schreibt es etwa 247 Tokens pro Sekunde.

Es gibt noch keine kostenlose API dafür. Die Gewichte sind offen: Du kannst sie von Hugging Face unter der Apache 2.0-Lizenz herunterladen. Arena hat es noch nicht bewertet: Wir fügen die Punktzahl hinzu, sobald die Stimmen eintreffen.

Compare WeVisOne VL 2B with every free model, and check what your own GPU can run, on FreeLLMArena.