Model library / ccore
A 4.5 billion-parameter Qwen3.5-based model that generates Three.js code and GLB assets from text prompts.
Parameters in total
Context length in tokens, as published
Weights at the released precision
Licence declared on the repository
Overview
CCORE GLB-3D-Coder is a specialised 4 billion-parameter coding model built on Qwen3.5-4B. It converts English descriptions of characters, props, buildings or environments into complete Three.js HTML/JavaScript pages that include a preview and an Export GLB button, allowing assets to be imported into Godot or other GLB-compatible editors.
The model ships with 4.5 billion parameters in float32 format, a context window of 262 144 tokens and no expert layers. Weights are released under the Apache-2.0 licence in Q4_K_M, Q8_0 and original Safetensors formats. It can be loaded via GGUF or the original checkpoint, and the large context length permits generation of extensive HTML and asset code in a single request.
Specification
| Repository | ccore/Qwen3.5-4B-GLB-3D-Coder |
| Publisher | ccore |
| Published | 1 November 2026 |
| Architecture | Qwen3_5ForConditionalGeneration |
| Model type | qwen3_5 |
| Parameters | 4,539,265,536 |
| Layers | 32 |
| Hidden size | 2,560 |
| Attention heads | 16, 4 key/value heads |
| Context length | 262,144 tokens |
| Vocabulary | 248,320 tokens |
| Weight format | float32 |
| Licence | apache-2.0 |
| Base model | Qwen/Qwen3.5-4B |
Memory
Parameter count multiplied by the bytes each format uses. The key-value cache comes on top.
| Precision | Weights | Notes |
|---|---|---|
| bf16 | 8.5 GiB | Full precision as released |
| fp8 | 4.2 GiB | 8-bit, near-lossless on most models |
| int4 | 2.1 GiB | 4-bit, smallest footprint |
The cache costs 128 KiB per token at 16-bit, so the full 262,144-token context of one request needs about 32.0 GiB. Concurrency multiplies that number, not the weights.
Hardware
At the released precision, with 90% of the card given to the server and 2.5 GiB kept for the runtime. The context column is what is left for the cache on that setup.
| GPU | Cards needed | Free for cache | Context it holds |
|---|---|---|---|
| RTX 4090 24GB | 1 | 2.8 GiB | about 23,028 tokens |
| RTX 5090 32GB | 1 | 10.0 GiB | about 82,011 tokens |
| L40S 48GB | 1 | 24.4 GiB | about 199,976 tokens |
| A100 80GB | 1 | 53.2 GiB | the full 262,144 tokens |
| H100 80GB | 1 | 53.2 GiB | the full 262,144 tokens |
| RTX PRO 6000 96GB | 1 | 67.6 GiB | the full 262,144 tokens |
| H200 141GB | 1 | 108.1 GiB | the full 262,144 tokens |
Serving
A vLLM launch line for the shape above. Check the model card for a runtime the publisher recommends.
vllm serve ccore/Qwen3.5-4B-GLB-3D-Coder \ --max-model-len 20480 \ --gpu-memory-utilization 0.90
Questions
The weights take about 16 GiB at the released precision. That fits on one RTX 4090 24GB, which leaves roughly 3 GiB for the key-value cache.
The repository declares apache-2.0. Read the licence text before commercial use: the name alone does not tell you what is allowed.
The configuration allows 262,144 tokens. Whether the whole window is usable depends on the memory left for the cache, which the hardware table works out per card.
This page is a reference, and Aiqre does not serve this model today. We deploy open-weight models on dedicated EU hardware on request, so if you want an OpenAI-compatible endpoint for it, email [email protected] with the model name and roughly what volume you expect.
Also in the library
Spark-X2.6-4B is a 4.1 billion-parameter, open-weight language model designed for on-device, general-purpose tasks.
Spark-X2.6-4B is a 4.1 B parameter causal language model from XHToken designed for on-device AI tasks.
Granite Switch 4.1 8B is a modular 8.8 billion-parameter language model that combines a base LLM, decision and safety adapters, a…
EdgeRock-4B is a 4.6 billion-parameter multimodal language model with constant-memory reasoning capabilities.
Hosting
Tell us the model and roughly what volume you expect. We reply with a price and an OpenAI-compatible endpoint, with your prompts never stored.