Skip to content
Local AI Wizard
Your machine
Theme

Local vision models

Video to text · Understand images and video: describe, answer questions, read documents, detect and segment.

No ranking for this task yet

No model in this sub-task is on the LMArena vision leaderboard, so no ranking is drawn. The table lists every catalog group with its Hub facts.

4 model groups · catalog checking Sep 26, 2026

Local vision models
Video-XL-2BAAI · Apache 2.0Not on the LMArena vision leaderboard of 2026-10-198.17Apache 2.0safetensors · transformersJun 6, 2025
Keye-VL-1_5-8BKwai-Keye · Apache 2.0Not on the LMArena vision leaderboard of 2026-10-198.77Apache 2.0transformers · safetensorsFeb 5, 2026
nemotron-labs-audio-visual-flamingo-hfnvidia · Publisher termsNot on the LMArena vision leaderboard of 2026-10-198.77Publisher termssafetensors · transformersJul 20, 2026
cogvlm2-llama3-captionzai-org · Publisher termsArena rated the chat model CogVLM2 Llama3 Chat 19B; this repository is the captioning model12.510Publisher termssafetensors · transformersMay 14, 2025
Publishers

4 publishers in this task

Most common license

Apache 2.0 (2)

Memory estimates

4 of 4 groups, from Hub parameter counts

Choose your machine and the charts and tables mark what fits in its memory.