Qwen has updated the model card for version 3.8, detailing native vision capabilities that allow it to process images and videos up to one hour in length. This information was shared via a Mastodon post by user 1337hero. AI
IMPACT Details on Qwen 3.8's enhanced vision capabilities could inform developers integrating multimodal AI.
RANK_REASON Model card update with technical details about capabilities. [lever_c_demoted from research: ic=1 ai=1.0]
Read on Mastodon — fosstodon.org →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →