Instructions to use ccore/Qwen3-1.7B-GLB-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/Qwen3-1.7B-GLB-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/Qwen3-1.7B-GLB-3D-Coder:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ccore/Qwen3-1.7B-GLB-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/Qwen3-1.7B-GLB-3D-Coder:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ccore/Qwen3-1.7B-GLB-3D-Coder:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf ccore/Qwen3-1.7B-GLB-3D-Coder:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf ccore/Qwen3-1.7B-GLB-3D-Coder:Q4_K_M

Use Docker

docker model run hf.co/ccore/Qwen3-1.7B-GLB-3D-Coder:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use ccore/Qwen3-1.7B-GLB-3D-Coder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ccore/Qwen3-1.7B-GLB-3D-Coder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ccore/Qwen3-1.7B-GLB-3D-Coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ccore/Qwen3-1.7B-GLB-3D-Coder:Q4_K_M

Ollama
How to use ccore/Qwen3-1.7B-GLB-3D-Coder with Ollama:
```
ollama run hf.co/ccore/Qwen3-1.7B-GLB-3D-Coder:Q4_K_M
```
Unsloth Desktop

How to use ccore/Qwen3-1.7B-GLB-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/Qwen3-1.7B-GLB-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/Qwen3-1.7B-GLB-3D-Coder:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ccore/Qwen3-1.7B-GLB-3D-Coder with Docker Model Runner:
```
docker model run hf.co/ccore/Qwen3-1.7B-GLB-3D-Coder:Q4_K_M
```

Lemonade

How to use ccore/Qwen3-1.7B-GLB-3D-Coder with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ccore/Qwen3-1.7B-GLB-3D-Coder:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-1.7B-GLB-3D-Coder-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use ccore/Qwen3-1.7B-GLB-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/Qwen3-1.7B-GLB-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/Qwen3-1.7B-GLB-3D-Coder:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ccore/Qwen3-1.7B-GLB-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/Qwen3-1.7B-GLB-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/Qwen3-1.7B-GLB-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"

CCORE GLB-3D-Coder 1.7B

Final checkpoint for the 1.7B GLB experiment

The model weights were last updated on November 13, 2026 at 00:15:34 UTC. If you downloaded a GGUF before this update, delete the local copy and download the updated file.

The main tests used F16 and Q8_0. In testing, Q4_K_M produced substantially lower-quality outputs.

Generate Three.js game assets and export them as GLB on modest hardware.

I fine-tuned Qwen3-1.7B on the CCORE GLB dataset to write complete HTML pages with an interactive 3D preview and a GLB export button.

Why Qwen3-1.7B?

I wanted to see how far a small model could go on this task while keeping full causal attention with grouped-query attention across all 28 layers. The goal is a short iteration loop for people with limited VRAM or no dedicated GPU. The Q8_0 file is about 1.83 GB and is my suggested starting point for CPU or low-VRAM use. Generation speed depends on the hardware, runtime, context length, and how much code the model writes.

Examples

Frames from the showcase. The prompts below are suggestions for similar assets.

Asset	Asset
Jungle command post	Stone golem boss
Desert command post	Frozen goblin camp
Bakery display counter	Low-poly iron table
Magic sword

Asset	Example prompt
Jungle command post	`Create a reinforced jungle command post with a watchtower, palm trees, and a perimeter fence.`
Stone golem boss	`Create a stone golem boss with chunky rock limbs and a glowing green crystal core.`
Desert command post	`Create a compact desert command post with a bunker, sandbags, and radio antennas.`
Frozen goblin camp	`Create a frozen goblin watch camp with snowy pine trees, a lookout tower, and a campfire.`
Bakery display counter	`Create a bakery display counter with a glass case, loaves of bread, and wicker baskets.`
Iron table	`Create a low-poly iron table with a riveted top and a lower shelf.`
Magic sword	`Create a low-poly magic sword with a blue blade, a crescent-shaped guard, and a glowing display pedestal.`

Weights and release status

GGUF	Approx. size	Notes
Q4_K_M	1.11 GB	Smallest download
Q8_0	1.83 GB	Suggested starting point for local testing
F16	3.45 GB	16-bit weights

All three GGUFs come from the same checkpoint. The FP16 Safetensors weights are also available for Transformers, along with the model configuration and tokenizer.

Quick start

Load the GGUF in a Qwen3-compatible runtime such as llama.cpp or LM Studio.
Use the system prompt below and describe the asset you want.
Save the generated HTML to a file and open it in a browser.
Click Export GLB and open the downloaded asset in your 3D editor.

Recommended sampling

Setting	Value
Temperature	0.8
Top K	40
Top P	0.95
Min P	0.0
Repeat penalty	1.0

System prompt

Create game assets for the Godot editor, which uses GLB files. Create whatever the user requests as a good-quality low-poly asset using only Three.js in one complete standalone HTML file. The HTML must show the asset and include an Export GLB button that downloads a working GLB. If the requested asset needs animation, add it and include the animation in the exported GLB; otherwise make it static.

Training domains

40 domains represented in the GLB dataset

Characters and creatures — Characters and NPCs, civilian characters, fantasy adventurers, modern specialists, companions and creatures, creatures and companions, enemies, enemies and bosses, bosses, robots and constructs.
Items and props — Weapons and armor, weapons/armor/equipment, items/tools/pickups, props and furniture, furniture and interiors, household appliances, electronics and optics, musical instruments, workshop and repair.
Environments and structures — Nature and environment, nature and garden, modular architecture, battlefield scenery, underwater structures, camping and travel, farming and homestead, urban services.
Vehicles and machines — Ground transport, air and space transport, watercraft, industrial machinery.
Activities and interactive assets — Cuisine and markets, festivals and ceremonies, sports and playgrounds, fitness and rehabilitation, laboratory and medical, museums and field research, interactive objects, traps and hazards, puzzles and gameplay markers.

Current limitations

In my tests, the model usually produces a 3D asset. Some attempts fail to render or export as GLB and may need a retry.

Support

Future model and dataset releases depend on community support. If you find this project useful, your contribution helps me cover GPU costs and keep those releases going. Support the project on Ko-fi.

Currency	Network	Address
BTC	Bitcoin (SegWit)	`bc1qr2gnr9g0uzk8rmsq0k6xpjgg4l7r0rfyrq69e6`
ETH	Ethereum Mainnet (ERC20)	`0xa17608FCdeAd9e717Cd42e04127175527b4E75CB`
SOL / USDC / USDT	Solana	`GhNmYmezKi1uWGKZeVxgddjiRW2rYNHZrf84ZaMcnha`