Dev Radar
Support
LiveUpdated 2026-09-19 22:52 UTC

ZDTaichu5.0-9B takes the Qwen3.5-9B backbone and pushes it beyond generic multimodal AI…

ZDTaichu5.0-9B takes the Qwen3.5-9B backbone and pushes it beyond generic multimodal AI into spatial reasoning,…

This is a dev post classified by Jev as Other (a tool drop), kept by the Dev Radar because it carries real work, not commentary.

ZDTaichu5.0-9B takes the Qwen3.5-9B backbone and pushes it beyond generic multimodal AI into spatial reasoning, embodied intelligence, and agentic tool use. TaichuAI took the Qwen3.5-9B language backbone, added Nvidia's C-RADIOv4-H vision encoder, and added ... 👁️ image + video understanding 🧭 spatial reasoning 🤖 agent/tool use 🦾 embodied AI 📚 128K context 🖼️ any-resolution vision And the author-reported numbers are interesting. 📋 ViewSpatial ZDTaichu — 62.5 Qwen3.5-9B — 48.2 Gemini 3 Pro — 50.4 GPT-5.2 — 47.3 MindCube-tiny ZDTaichu — 78.3 Qwen3.5-9B — 57.6 Gemini 3 Pro — 70.9 GPT-5.2 — 60.

Posted by David Hendrickson (11.1k followers) 3 days ago · 19 likes · 1.9k views · view the original post on X. Kept by the Dev Radar as Other.

More dev work like this

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.