QW

Qwen3.5-4B-3D-Coder

QwenGGUF by ReallyFloppyPenguinUpdated 2026-10-28
Download on Hugging Face
Parameters4.21B
Context256K
Layers32
Architectureqwen35
Smallest quant2.7 GB
Quick answer

Qwen3.5-4B-3D-Coder needs about 4.3 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Qwen3.5-4B-3D-Coder – 4B model for coding and 3D scene generation

Qwen3.5-4B-3D-Coder is a 4.21B parameter model fine‑tuned for general coding and high‑quality 3D scene generation with Three.js. It supports coding, reasoning, and tool usage. The model is released under Apache‑2.0 and is available in a Q4_K_M GGUF split.

Good at

  • Coding in JavaScript and HTML
  • Generating 3D scenes with Three.js
  • Reasoning with tool calls

Limits

  • No vision or audio support
  • Requires split GGUF shards
  • Large memory for 8k context

Best for

  • WebGPU 3D scene generation
  • JavaScript code generation
  • Interactive coding demos

Who it’s for. Developers and researchers working on web‑based 3D applications and code generation. The model is suitable for those who need a lightweight, open‑source alternative to larger 3D‑focused LLMs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.7 GB (7 parts) 4.3 GB
Fits Get file →

The Q4_K_M quantized file is 2.71 GB and requires approximately 4.3 GB of VRAM at 8k context. It is split into 7 shards of 512 MB or less, making it compatible with browsers and WebGPU. For systems with 8 GB VRAM, Q4_K_M is the recommended quant.

What GPU do you need for Qwen3.5-4B-3D-Coder?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q4_K_M (2.7 GB file, about 4.3 GB in use).

Which Qwen3.5-4B-3D-Coder quant should you choose?

Q4_K_M is the usual starting point for Qwen3.5-4B-3D-Coder: it balances file size and quality well. Here it is a 2.7 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters4.21B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

FamilyQwen
Licenseapache-2.0
Downloads (HF)705
Last updated2026-10-28

Frequently asked questions about Qwen3.5-4B-3D-Coder

How much VRAM does Qwen3.5-4B-3D-Coder need?

About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.7 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Qwen3.5-4B-3D-Coder on an 8 GB GPU?

Yes, with Q4_K_M: the 2.7 GB file needs about 4.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3.5-4B-3D-Coder GGUF?

It depends on the quant: Q4_K_M is 2.7 GB.

What context length does Qwen3.5-4B-3D-Coder support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Qwen3.5-4B-3D-Coder GGUF?

The files are on Hugging Face in the ReallyFloppyPenguin/Qwen3.5-4B-3D-Coder-GGUF-split repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Qwen3.5-4B-3D-Coder use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Qwen3.5-4B-3D-Coder on 8 GB VRAM?

Yes, the Q4_K_M GGUF requires about 4.3 GB VRAM at 8k context, leaving headroom for other processes.

Does the model support image or video input?

No, the model has no vision or audio capabilities.

How many shards does the GGUF file contain?

The Q4_K_M GGUF is split into 7 shards, each 512 MB or less.

Other GGUFs of Qwen3.5-4B-3D-Coder

Similar models

Browse all →

More from ReallyFloppyPenguin

All by ReallyFloppyPenguin →

More Qwen models

All Qwen →

Other small models

All small models →