Qwen3.5-4B-3D-Coder: a 4B model that writes working Three.js scenes in one shot
Independent fine-tune of Qwen3.5-4B for general coding with a focus on interactive 3D scenes; full FP16 weights, a training dataset of 4,146 scenes, and a technical report landed on Oct 28.
Why it matters
A 4B model small enough to run locally that emits complete, self-contained Three.js HTML in one shot, plus a public dataset with thinking traces for reproducing it.
What you could build with it
A teacher building interactive science lessons could generate a 3D scene per topic, a canal lock, a volcano, a solar system, from a plain prompt, embedding the self-contained HTML in lesson pages without hiring a 3D artist.
Does it hold up?
Promising but early: the author's own tests show one-shot success improved substantially across the Oct 25-27 checkpoints, yet some scenes still need a retry or correction, and independent benchmarks do not exist yet.
Built with Qwen3.5-4B-3D-Coder
- Edition 054: OpenAI hands the verdict to outsiders while small models swallow the edgenewsletter · Newsletter roundup flagging the model as the clearest sign yet of how far local coding models have come, noting the Oct 27 checkpoint fix and the Oct 28 full release plan.
Learn more
First spotted on hf: source.
More AI models
OpenAI publishes 722 AI-generated math manuscripts from an unreleased modelOpenAI released 722 mathematical manuscripts in 372 result families to GitHub under Apache-2.0, produced by an…models · JEV 0.74Tencent Hunyuan Hy3: open 295B MoE with 21B active under Apache 2.0Tencent open-sourced Hy3, a 295B-parameter mixture-of-experts model with only 21B parameters active per token, under…models · JEV 0.73NVIDIA Isaac Lab 3.0 GA + Isaac OS open runtime + Agile ONE SN humanoidMajor Isaac platform expansion at GTC Berlin Oct 21: Isaac Lab 3.0 is generally available as the open-source robot…models · JEV 0.73StepFun Step-5-Preview — open BF16 weights releasedStepFun published the full BF16 weights for its flagship Step-5-Preview agentic model (600B-parameter sparse MoE, 27B…models · JEV 0.73NVIDIA Nemotron 3.5 Retriever collection: Embed 8B/1B, Rerank 8B, Parse 631MNVIDIA's Oct 21 collection drop for agentic retrieval: Nemotron-3.5-Embed in 8B BF16, 1B BF16 and 1B NVFP4…models · JEV 0.72Kimi K3.1 Pro: Moonshot's 2.8T open-weight flagship officially launchesMoonshot AI officially launched Kimi K3.1 Pro on Oct 23, a mixture-of-experts model with 2.8 trillion total / 104…models · JEV 0.72
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.