🤯 We get excited when Qwen drops a new model and here is one.
This is a dev post classified by Jev as Other (a launch), kept by the Dev Radar because it carries real work, not commentary.
🤯 We get excited when Qwen drops a new model and here is one. It’s its next gen multimodal Omni model (an AI that can read, see, listen and watch video) with a 1M token context. Qwen3.8-Omni-Flash is essentially the new generation after Qwen3.5-Omni trained for understanding … 📝 Text 🖼️ Images 🎧 Audio 🎥 Video But this caught my attention. 👇 Instead of processing an enormous video from beginning to end, Qwen built an agentic video-understanding mode that can decide where inside the video it needs to look and listen. On OmniVideoBench: 🎯 Accuracy: 63.4 → 67.8 🧠 Tokens/query: 145,736 → 7
Posted by David Hendrickson (11.1k followers) 2 days ago · 83 likes · 9.4k views · view the original post on X. Kept by the Dev Radar as Other.
More dev work like this
- We’ve evaluated NVIDIA GR00T N1.7 on VLA-Replica! Check out Alex @alexhuang1029's post… — @YuXiang_IRVL
- You can run locally Uncensored Ternary Bonsai 2-27B Same 5.9GB file. — @0x0SojalSec
- dear rtx 3060 owners, and every 12gb card behind it. bonsai 2 27b dense went from 26 to… — @sudoingX
- Nice: banked codex reset for all of us. — @kimmonismus
- Nvidia dropped an official DeepSeek-V4.1-Flash NVFP4 build. — @TeksEdge
- Convolutional Neural Networks. #BigData #Analytics #DataScience #AI #MachineLearning… — @gp_pulipaka
- Reinforcement Learning and Optimal Control! #BigData #Analytics #DataScience #AI… — @gp_pulipaka
- The #Mathematical #Programming - #FPGA. #BigData #Analytics #DataScience #AI… — @gp_pulipaka
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 15.1k posts from 4.7k X accounts over the last 21 days, 1.7k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 22:52 UTC. Full method.