Tencent's WeVisOne-VL-2B model card lands on Hugging Face
tencent · hf · 2026-10-22
Tencent's WeVisOne-VL-2B model card is live on Hugging Face with an image-text-to-text pipeline. Built on Qwen3-VL, it covers vision-language tasks including object detection, referring expression comprehension, object counting, point grounding, and OCR.
Related event: Tencent Open-Sources WeVisOne-VL for Unified Visual Perception(3 posts)→
More from Models
- Local Run of Suspected DeepSeek-4.1-Flash Hits 670 TPS on 4x RTX Pro 6000 — Kyrannio · 2026-10-23
- Local LLM benchmark drama: unrepeatable scores spark call for AIPerf standard — TheZachMueller · 2026-10-23
- Dev plans to point an abliterated local model at his smart TV to strip spyware — TheZachMueller · 2026-10-23
- Claude $200 plan delivers 45.3x API value, author denies Anthropic quota cut — RexDouglass · 2026-10-23
- User slams OpenAI's GPT-6.1 Sol: 20 hours lost, ignores human feedback — RexDouglass · 2026-10-23
- Dexmal's open-source VLA model DM0.5 lands in LeRobot, tops RoboColiseum — AdinaYakup · 2026-10-23