Qwen3.5-4B-3D-Coder-GGUF
Qwen3.5-4B-3D-Coder is an early-preview independent fine-tune of
Qwen3.5-4Bby ccore, exploring general-purpose coding and interactive 3D scene generation using self-contained Three.js HTML and JavaScript. It was trained on the MIT-licensed ccore Three.js 3D Scenes dataset, containing 4,146 examples with prompts, reasoning traces, complete code, and complexity labels. The repository includes FP16 safetensors, Q4_K_M and Q8_0 GGUF builds, and a technical report. An October 27 checkpoint reportedly improves one-shot generation and scene quality. No quantitative benchmark results are provided; evaluation is demonstrated through sample 3D scenes. Released under Apache-2.0, it includes recommended sampling settings and a Three.js-focused system prompt. LM Studio users should disable multi-token prediction. Some generations may still require retries or minor code corrections.
[!NOTE] MTP — Speculative Decoding: No | MTP Version Available Here — Qwen3.5-4B-3D-Coder-MTP-Repacked
Model Files
| File Name | Quant Type | File Size | File Link | Description |
|---|---|---|---|---|
| Qwen3.5-4B-3D-Coder.BF16.gguf | BF16 | 8.42 GB | Link | Full BF16 weights. Highest quality, largest file size. |
| Qwen3.5-4B-3D-Coder.Q3_K_L.gguf | Q3_K_L | 2.42 GB | Link | Lower quality but usable, good for low RAM availability. |
| Qwen3.5-4B-3D-Coder.Q3_K_M.gguf | Q3_K_M | 2.26 GB | Link | Low quality. |
| Qwen3.5-4B-3D-Coder.Q4_K_M.gguf | Q4_K_M | 2.71 GB | Link | Good quality, default size for most use cases, recommended. |
| Qwen3.5-4B-3D-Coder.Q4_K_S.gguf | Q4_K_S | 2.56 GB | Link | Slightly lower quality with more space savings, recommended. |
| Qwen3.5-4B-3D-Coder.Q5_K_M.gguf | Q5_K_M | 3.07 GB | Link | High quality, recommended. |
| Qwen3.5-4B-3D-Coder.Q5_K_S.gguf | Q5_K_S | 2.99 GB | Link | High quality, recommended. |
| Qwen3.5-4B-3D-Coder.Q6_K.gguf | Q6_K | 3.46 GB | Link | Very high quality, near perfect, recommended. |
| Qwen3.5-4B-3D-Coder.Q8_0.gguf | Q8_0 | 4.48 GB | Link | Extremely high quality, generally unneeded but max available quant. |
| Qwen3.5-4B-3D-Coder.mmproj-bf16.gguf | mmproj-bf16 | 676 MB | Link | Multimodal projection file in BF16 format. Used for vision/language models. |
llama.cpp
LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp