Instructions to use ccore/Qwen3.5-4B-3D-Coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ccore/Qwen3.5-4B-3D-Coder with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ccore/Qwen3.5-4B-3D-Coder:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ccore/Qwen3.5-4B-3D-Coder:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ccore/Qwen3.5-4B-3D-Coder:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ccore/Qwen3.5-4B-3D-Coder:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf ccore/Qwen3.5-4B-3D-Coder:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ccore/Qwen3.5-4B-3D-Coder:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf ccore/Qwen3.5-4B-3D-Coder:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ccore/Qwen3.5-4B-3D-Coder:Q4_K_M

Use Docker

docker model run hf.co/ccore/Qwen3.5-4B-3D-Coder:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use ccore/Qwen3.5-4B-3D-Coder with Ollama:
```
ollama run hf.co/ccore/Qwen3.5-4B-3D-Coder:Q4_K_M
```
Unsloth Desktop

How to use ccore/Qwen3.5-4B-3D-Coder with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ccore/Qwen3.5-4B-3D-Coder:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ccore/Qwen3.5-4B-3D-Coder:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ccore/Qwen3.5-4B-3D-Coder with Docker Model Runner:
```
docker model run hf.co/ccore/Qwen3.5-4B-3D-Coder:Q4_K_M
```

Lemonade

How to use ccore/Qwen3.5-4B-3D-Coder with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ccore/Qwen3.5-4B-3D-Coder:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-4B-3D-Coder-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use ccore/Qwen3.5-4B-3D-Coder with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ccore/Qwen3.5-4B-3D-Coder:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default ccore/Qwen3.5-4B-3D-Coder:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ccore/Qwen3.5-4B-3D-Coder with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ccore/Qwen3.5-4B-3D-Coder:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "ccore/Qwen3.5-4B-3D-Coder:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Qwen3.5-4B-3D-Coder

Early preview · General coding with a focus on 3D

An experiment exploring the feasibility of small language models for general-purpose coding and high-quality 3D scene generation.

This is an early preview of a 4B model I am still training, with a particular focus on creating interactive 3D scenes with Three.js. Initial hands-on results have been promising for coding in general, and especially for generating 3D scenes, so I decided to share the progress while development continues.

This is an independent fine-tune by CCORE, based on Qwen/Qwen3.5-4B. It is not an official Qwen release.

Technical report — now available

The technical report for this training experiment is now available.

Read the technical report (PDF) · Download the PDF

Full FP16 weights — now available

The original FP16 weights are now available in this repository in Safetensors format, alongside the Q4_K_M and Q8_0 GGUF versions.

The release includes all four weight shards, the model configuration, tokenizer, generation configuration, chat template, and image/video processor settings. The FP16 weights were verified locally for loading and text generation with Transformers 5.20.2.

The FP16 generation defaults use temperature 0.6, top-k 20, top-p 0.95, and repetition penalty 1.0, with caching enabled.

Browse the FP16 files and GGUF versions

Training dataset — now available

The dataset used to train this model is now public: CCORE Three.js 3D Scenes.

It contains 4,146 scene examples (3,933 training / 213 validation), including prompts, full thinking traces, complete HTML/JavaScript responses, and complexity levels. Rendered reference images are available in the optional previews configuration. The dataset is released under the MIT License.

October 27 checkpoint update

Both Q4_K_M and Q8_0 now contain the updated October 27 checkpoint. If you downloaded an earlier version, please download the files again to get this update.

In my latest tests, one-shot success has improved substantially, along with overall scene quality. Some scenes can still require another attempt or a correction.

Generation parameters remain unchanged for both quantizations. Use the settings listed below. The earlier fix for the layer-related issue reported by some users is also included.

The comparison below shows the Rome scene across the October 25, 26, and 27 previews.

Release update — October 29, 2026

The full FP16 weights, training dataset, and technical report (PDF) are now available.

The full set of quantized versions is also planned.

Early examples

Selected screenshots of rendered Three.js scenes: stylized architecture, gardens, voxel environments, furniture, workshop interiors, and mechanical objects, built through HTML and JavaScript.

Click any image to view the original screenshot at full size.

Sakura Temple Garden	Sunset Village
Dragonrider Aerie	Voxel launch site
The Bookbinding Bench	LGA 3647 Socket
Pelican Bike No. 07	Bow-Front Secretary Desk
Kōrin Garden	Sakura bonsai

Generation settings

Use the following settings for both the Q4_K_M and Q8 versions:

Parameter	Value
Temperature	0.6–0.8
Top P	0.90–0.95
Repeat penalty	1.0
Top K	20–40

LM Studio: disable MTP

Important: If you're running this model in LM Studio, disable multi-token prediction (MTP) for the model to work properly. LM Studio enables this option by default.

System prompt for Three.js scenes

Use only the Three.js core ES module from
https://cdnjs.cloudflare.com/ajax/libs/three.js/0.160.0/three.module.min.js.
Do not import addons or legacy examples/js paths;
implement any camera controls directly inside the HTML.

Example prompts

Use the system prompt above, then try one of these user prompts.

Elephant rehabilitation habitat

Please create one self-contained HTML file with Three.js from cdnjs showing
an elephant rehabilitation habitat.

A broad sheltered yard connects water, shade, and feeding areas through
accessible paths. Use the elephant's scale and movement clearance to guide
the layout around the structures.

Render it as a deliberate 3D voxel model built from visible cubic blocks,
with clear depth, readable silhouettes, and solid spatial relationships.

Dragonrider aerie on a sea stack

Build a self-contained HTML scene with Three.js from cdnjs featuring a
dragonrider aerie on a sea stack, with perches, a hatchery, and a windlass.

The aerie occupies a flat-topped sea stack, reached by a rope windlass from
the shore. Four projecting stone perches ring the central hatchery, a
vaulted cave with sand nests and a smoke hole. A timber landing deck holds
a hoist crane and harness racks, while switchback stairs connect the
perches to a water-level boathouse.

Render it as a deliberate 3D voxel model built from visible cubic blocks,
with clear depth, readable silhouettes, and solid spatial relationships.

Canal lock and weir complex

Please create one self-contained HTML file with Three.js from cdnjs showing
a canal lock and weir complex with a central island.

Animated air traffic control tower

Make a standalone HTML scene with Three.js from cdnjs depicting an animated
air traffic control tower with rotating radar and light signals.

A tapered control tower rises from a rectangular base to a cantilevered
glass cab with angled glazing panels and an external catwalk. A primary
surveillance radar on a roof pedestal turns continuously, and a rotating
beacon sits above the cab.

Known issues

The bugs observed so far have generally involved duplicate variable names, rather than major structural problems.

Downloads last month: 6,944

Safetensors

Model size

5B params

Tensor type

F16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ccore/Qwen3.5-4B-3D-Coder

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

(1154)

this model

Quantizations

1 model

ccore
/

Qwen3.5-4B-3D-Coder

Qwen3.5-4B-3D-Coder

Early preview · General coding with a focus on 3D

Technical report — now available

Full FP16 weights — now available

Training dataset — now available

October 27 checkpoint update

Release update — October 29, 2026

Early examples

Generation settings

LM Studio: disable MTP

System prompt for Three.js scenes

Example prompts

Elephant rehabilitation habitat

Dragonrider aerie on a sea stack

Canal lock and weir complex

Animated air traffic control tower

Known issues

Model tree for ccore/Qwen3.5-4B-3D-Coder

Dataset used to train ccore/Qwen3.5-4B-3D-Coder

Space using ccore/Qwen3.5-4B-3D-Coder 1