# CCORE releases Qwen3.5-4B-3D-Coder for Three.js scene generation

> Original title: Describe a scene, then build it in Three.js. Qwen3.5-4B-3D-Coder is CCORE's open-weight fine-tune of Qwen3.5-4B for interactive 3D scene ...

- Source: ModelScope
- Published: 2026-11-04T08:12:50.000Z
- Bad Influence: https://badinfluence.news/items/ja5uxwiuxq8rt2xpwt2h05nqk
- Original: https://x.com/ModelScope2022/status/2117892816370307200

## Summary

CCORE has released Qwen3.5-4B-3D-Coder, an open-weight fine-tune of Qwen3.5-4B that generates editable HTML and JavaScript Three.js scenes from text descriptions, available as an early preview. The model supports image-guided generation through Q4_K_M and Q8_0 GGUF versions, and FP16 weights run with Transformers. The model is licensed under Apache 2.0 and its 4,146-example training dataset under MIT.

## Post

Describe a scene, then build it in Three.js. Qwen3.5-4B-3D-Coder is CCORE's open-weight fine-tune of Qwen3.5-4B for interactive 3D scene generation, available as an early preview.
🤖 https://modelscope.ai/models/ccore/Qwen3.5-4B-3D-Coder

🧊 Generate scene code: Create editable HTML and JavaScript for architecture, interiors, gardens, and voxel environments.
🖼️ Use visual references: Q4_K_M and Q8_0 GGUF versions support image-guided generation with the original Qwen3.5-4B vision projector. Outputs interpret the reference rather than reproduce every detail.
💻 Run locally: FP16 weights support Transformers; GGUF versions include llama.cpp setup instructions.
📚 Explore the training data: 4,146 scene examples include prompts, reasoning traces, and complete HTML/JavaScript responses.
📜 Model: Apache 2.0. Dataset: MIT.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWREMIgaAAA_HwD.jpg&mode=thumb&exp=1794009600&sig=34b2036b14d6b29b)