Instructions to use ccore/CCORE-Web-Coder-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use ccore/CCORE-Web-Coder-4B 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/CCORE-Web-Coder-4B:Q8_0 # Run inference directly in the terminal: llama cli -hf ccore/CCORE-Web-Coder-4B:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf ccore/CCORE-Web-Coder-4B:Q8_0 # Run inference directly in the terminal: llama cli -hf ccore/CCORE-Web-Coder-4B:Q8_0
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/CCORE-Web-Coder-4B:Q8_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf ccore/CCORE-Web-Coder-4B:Q8_0
Use Docker
docker model run hf.co/ccore/CCORE-Web-Coder-4B:Q8_0
- Llama new
- LM Studio
- Jan
- vLLM
How to use ccore/CCORE-Web-Coder-4B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ccore/CCORE-Web-Coder-4B" # 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/CCORE-Web-Coder-4B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/ccore/CCORE-Web-Coder-4B:Q8_0
- Ollama
How to use ccore/CCORE-Web-Coder-4B with Ollama:
ollama run hf.co/ccore/CCORE-Web-Coder-4B:Q8_0
- Unsloth Desktop
- Pi
How to use ccore/CCORE-Web-Coder-4B with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ccore/CCORE-Web-Coder-4B:Q8_0
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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "ccore/CCORE-Web-Coder-4B:Q8_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use ccore/CCORE-Web-Coder-4B with Docker Model Runner:
docker model run hf.co/ccore/CCORE-Web-Coder-4B:Q8_0
- Lemonade
How to use ccore/CCORE-Web-Coder-4B with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ccore/CCORE-Web-Coder-4B:Q8_0
Run and chat with the model
lemonade run user.CCORE-Web-Coder-4B-Q8_0
List all available models
lemonade list
- Hermes Agent
How to use ccore/CCORE-Web-Coder-4B 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/CCORE-Web-Coder-4B:Q8_0
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://127.0.0.1:9931/v1 hermes config set model.default ccore/CCORE-Web-Coder-4B:Q8_0
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use ccore/CCORE-Web-Coder-4B with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ccore/CCORE-Web-Coder-4B:Q8_0
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://127.0.0.1:9931/v1 \ --custom-model-id "ccore/CCORE-Web-Coder-4B:Q8_0" \ --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"
Add Ko-fi and crypto support details to the model card
Browse files
README.md
CHANGED
|
@@ -40,8 +40,6 @@ CCORE Web Coder 4B turns a brief into a single React HTML document for a website
|
|
| 40 |
| Sunday, November 22, 2026 | Planned full release with Safetensors, Q8_0, and more quantizations |
|
| 41 |
| November 25, 2026 | Planned dataset release |
|
| 42 |
|
| 43 |
-
Community support helps cover data curation and GPU time for future open releases. [Support CCORE on Ko-fi](https://ko-fi.com/ccorecaio)
|
| 44 |
-
|
| 45 |
## Inference
|
| 46 |
|
| 47 |
Use the system prompt below and send your brief as the user message. Save the response as an `.html` file and open it in a browser.
|
|
@@ -110,6 +108,28 @@ The preview video shows example Q8_0 generation rates for a full page of around
|
|
| 110 |
|
| 111 |

|
| 112 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 113 |
## License
|
| 114 |
|
| 115 |
The preview is distributed under Apache 2.0. CCORE modified the base weights through fine-tuning and converted them to Q8_0 GGUF. [License](LICENSE)
|
|
|
|
| 40 |
| Sunday, November 22, 2026 | Planned full release with Safetensors, Q8_0, and more quantizations |
|
| 41 |
| November 25, 2026 | Planned dataset release |
|
| 42 |
|
|
|
|
|
|
|
| 43 |
## Inference
|
| 44 |
|
| 45 |
Use the system prompt below and send your brief as the user message. Save the response as an `.html` file and open it in a browser.
|
|
|
|
| 108 |
|
| 109 |

|
| 110 |
|
| 111 |
+
## Support the project
|
| 112 |
+
|
| 113 |
+
If this preview is useful to you, your support helps CCORE fund dataset curation and GPU time for future open releases.
|
| 114 |
+
|
| 115 |
+
### Ko-fi
|
| 116 |
+
|
| 117 |
+
[**Support CCORE on Ko-fi**](https://ko-fi.com/ccorecaio)
|
| 118 |
+
|
| 119 |
+
### Crypto donations
|
| 120 |
+
|
| 121 |
+
**Bitcoin (BTC) 路 Bitcoin Network (SegWit)**
|
| 122 |
+
|
| 123 |
+
`bc1qr2gnr9g0uzk8rmsq0k6xpjgg4l7r0rfyrq69e6`
|
| 124 |
+
|
| 125 |
+
**Ethereum (ETH) 路 Ethereum Mainnet (ERC20)**
|
| 126 |
+
|
| 127 |
+
`0xa17608FCdeAd9e717Cd42e04127175527b4E75CB`
|
| 128 |
+
|
| 129 |
+
**Solana (SOL / USDC / USDT) 路 Solana Network**
|
| 130 |
+
|
| 131 |
+
`GhNmYmezKi1uWGKZeVxgddjiRW2rYNHZrf84ZaMcnha`
|
| 132 |
+
|
| 133 |
## License
|
| 134 |
|
| 135 |
The preview is distributed under Apache 2.0. CCORE modified the base weights through fine-tuning and converted them to Q8_0 GGUF. [License](LICENSE)
|