The useful shift here is that a small language model can produce not just a 3D description, but the code for a previewable asset and an export path into common GLB workflows. That makes text-to-3D generation inspectable and editable rather than a black-box mesh handoff, though the generated code still needs review.
AI Model2026
CCORE GLB-3D-Coder
Turns text descriptions into Three.js scenes that can be previewed and exported as GLB, targeting low-poly game assets and procedural environments. Fine-tuned from Qwen3.5-4B; some outputs may need retries or code fixes.
Introduction
Information
- Websitehuggingface.co
- OrganizationsCCORE
- Published date2026/11/05
Categories
More Items
AI Image2026
Generates high-resolution images and edits multiple references in ComfyUI in 8 steps. Based on MiniMax-H3, it offers int8 and w4a8 variants, with the smallest setup using about 21 GB of peak VRAM at 8 MP.
AI Model2026
Quantizes DeepSeek-V4.1-Flash-1017’s routed MoE experts and activations to NVFP4 for inference deployment. It supports multimodal input and up to one million tokens of context, but requires NVIDIA Blackwell GPUs and compatible runtimes.
AI Model2026
Compresses the model by pruning half its experts and quantizing the retained weights, targeting code, agentic workflows, long context, and vision. It retains 94.8%–98.7% of the base model’s scores on two coding benchmarks, at the cost of broader capabilities.