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

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 Studio

How to use CoreWorxLab/caal-qwen3.5-2b with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for CoreWorxLab/caal-qwen3.5-2b to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for CoreWorxLab/caal-qwen3.5-2b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for CoreWorxLab/caal-qwen3.5-2b to start chatting

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 @mariozechner/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

Hermes Agent new

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 new

OpenClaw new

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"

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

CAAL Qwen3.5 2B — Fine-Tuned for Tool Calling

A fine-tuned Qwen3.5 2B model optimized for tool calling in voice assistant workflows. Built for CAAL (CoreWorxLab Ambient Assistant for Linux).

Performance

82/85 tests passed (96%) on the CAAL 85-test evaluation suite:

Category	Score
Single tool calls	27/27
Conversational (no tool)	10/10
Multi-turn chains	28/29
Argument formatting	17/19

Model Details

Base model: Qwen3.5 2B
Training method: SFT with BF16 LoRA (last-turn-only — previous turns as context, only final response trained)
LoRA config: r=32, alpha=32
Quantization: Q4_K_M (GGUF)
File size: ~1.2 GB
VRAM usage: ~2.6 GB at 16384 context

Usage with Ollama

# Download the GGUF and create a Modelfile:
# Modelfile contents:
# FROM caal-qwen3.5-2b-q4.gguf
# RENDERER qwen3.5
# PARSER qwen3.5
# PARAMETER temperature 0.1
# PARAMETER num_ctx 16384

ollama create caal-qwen35-2b -f Modelfile

Designed For

Edge deployment on consumer GPUs (fits on 5GB+ VRAM alongside TTS)
Local voice assistants with tool calling
Smart home control, email, calendar, and service management
Multi-step tool chains (e.g., search → lookup contact → send email)

License

See LICENSE for the CAAL Model License v1.0. This model is free for personal, non-commercial use with attribution to CoreWorxLab. Commercial use requires written permission.

The base model (Qwen3.5) is licensed under Apache 2.0. Users must comply with both licenses.