Instructions to use CoreWorxLab/caal-qwen3.5-2b 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 CoreWorxLab/caal-qwen3.5-2b 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 CoreWorxLab/caal-qwen3.5-2b # Run inference directly in the terminal: llama cli -hf CoreWorxLab/caal-qwen3.5-2b
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf CoreWorxLab/caal-qwen3.5-2b # Run inference directly in the terminal: llama cli -hf CoreWorxLab/caal-qwen3.5-2b
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 CoreWorxLab/caal-qwen3.5-2b # Run inference directly in the terminal: ./llama-cli -hf CoreWorxLab/caal-qwen3.5-2b
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 CoreWorxLab/caal-qwen3.5-2b # Run inference directly in the terminal: ./build/bin/llama-cli -hf CoreWorxLab/caal-qwen3.5-2b
Use Docker
docker model run hf.co/CoreWorxLab/caal-qwen3.5-2b
- LM Studio
- Jan
- Ollama
How to use CoreWorxLab/caal-qwen3.5-2b with Ollama:
ollama run hf.co/CoreWorxLab/caal-qwen3.5-2b
- Unsloth Desktop
- Pi
How to use CoreWorxLab/caal-qwen3.5-2b with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf CoreWorxLab/caal-qwen3.5-2b
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": "CoreWorxLab/caal-qwen3.5-2b" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use CoreWorxLab/caal-qwen3.5-2b with Docker Model Runner:
docker model run hf.co/CoreWorxLab/caal-qwen3.5-2b
- Lemonade
How to use CoreWorxLab/caal-qwen3.5-2b with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull CoreWorxLab/caal-qwen3.5-2b
Run and chat with the model
lemonade run user.caal-qwen3.5-2b-{{QUANT_TAG}}List all available models
lemonade list
- Hermes Agent
How to use CoreWorxLab/caal-qwen3.5-2b with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf CoreWorxLab/caal-qwen3.5-2b
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 CoreWorxLab/caal-qwen3.5-2b
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use CoreWorxLab/caal-qwen3.5-2b with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf CoreWorxLab/caal-qwen3.5-2b
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 "CoreWorxLab/caal-qwen3.5-2b" \ --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"
| CAAL Model License v1.0 | |
| Copyright (c) 2026 CoreWorxLab | |
| 1. Definitions | |
| "Model" β Any fine-tuned language model, LoRA adapter, training configuration, | |
| or model artifact produced by CoreWorxLab. | |
| "Training Data" β The datasets, examples, and scripts used to produce Models. | |
| "CAAL-Compatible System" β Any voice assistant or automation platform that | |
| integrates with CAAL for non-commercial, personal use. | |
| "Commercial Use" β Selling, licensing, or otherwise monetizing Models or | |
| Training Data as part of a product or service, including offering Models as a | |
| hosted service for paying customers. | |
| "CoreWorxLab" β The maintainer and operator of the CAAL project. | |
| 2. Grant of Rights | |
| Permission is granted, free of charge, to any person to: | |
| a. Use Models for personal, non-commercial purposes with any CAAL-Compatible | |
| System. | |
| b. Modify Models or Training Data for personal use or to contribute | |
| improvements back to the project. | |
| c. Share Models with attribution to CoreWorxLab. | |
| 3. Restrictions | |
| a. No Commercial Use by Third Parties. Models and Training Data may not be used | |
| commercially by anyone other than CoreWorxLab without prior written | |
| permission. This includes but is not limited to: | |
| - Bundling Models with a competing commercial product | |
| - Offering Models as a hosted or managed service | |
| - Reselling or sublicensing access to Models | |
| - Using Training Data to produce competing fine-tuned models for commercial | |
| purposes | |
| b. No Misrepresentation. Models may not be presented as the work of anyone | |
| other than CoreWorxLab. | |
| c. Attribution Required. Any permitted use of Models must include: | |
| - Credit to CoreWorxLab | |
| - A link to the original repository | |
| 4. Base Model Rights | |
| Models are fine-tuned derivatives of base models (e.g., Alibaba's Qwen3.5) | |
| which are subject to their own licenses. This license applies only to the | |
| fine-tuning artifacts, Training Data, and configurations produced by | |
| CoreWorxLab. Users must also comply with the base model's license terms. | |
| 5. No Warranty | |
| MODELS AND TRAINING DATA ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, | |
| EXPRESS OR IMPLIED. IN NO EVENT SHALL COREWORXLAB BE LIABLE FOR ANY CLAIM, | |
| DAMAGES, OR OTHER LIABILITY ARISING FROM USE OF THE MODELS. | |
| 6. Commercial Licensing | |
| For commercial use inquiries, contact CoreWorxLab at cmac@coreworxlab.com. | |