Instructions to use h-d-h/rad-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use h-d-h/rad-model 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 h-d-h/rad-model:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf h-d-h/rad-model:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf h-d-h/rad-model:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf h-d-h/rad-model: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 h-d-h/rad-model:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf h-d-h/rad-model: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 h-d-h/rad-model:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf h-d-h/rad-model:Q4_K_M

Use Docker

docker model run hf.co/h-d-h/rad-model:Q4_K_M

LM Studio
Jan
Ollama
How to use h-d-h/rad-model with Ollama:
```
ollama run hf.co/h-d-h/rad-model:Q4_K_M
```
Unsloth Desktop

How to use h-d-h/rad-model with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf h-d-h/rad-model: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": "h-d-h/rad-model:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use h-d-h/rad-model with Docker Model Runner:
```
docker model run hf.co/h-d-h/rad-model:Q4_K_M
```

Lemonade

How to use h-d-h/rad-model with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull h-d-h/rad-model:Q4_K_M

Run and chat with the model

lemonade run user.rad-model-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use h-d-h/rad-model with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf h-d-h/rad-model: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 h-d-h/rad-model:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use h-d-h/rad-model with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf h-d-h/rad-model: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 "h-d-h/rad-model: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"

rad-model

QLoRA fine-tune of Qwen 2.5 7B Instruct for Radicle and Git tool calling. Distributed as a GGUF file for local inference with llama.cpp.

Intended use

Tool-calling backend for CLI assistants that work with Radicle (decentralized code collaboration) and Git. The model selects and parameterizes the right CLI tool given a natural language request.

Training

Method: QLoRA (r=32, alpha=64) via Unsloth
Dataset: h-d-h/rad-model-dataset — ~870 synthetic tool-calling examples covering 89 tools
Hardware: NVIDIA RTX 3090 (24 GB VRAM)
Quantization: Q4_K_M (~4.5 GB)

Serving

llama-server -m rad-model-run6-q4_k_m.gguf --port 8080 -ngl 99 --host 0.0.0.0

The model serves an OpenAI-compatible /v1/chat/completions endpoint with tool-calling support.

Evaluation

Evaluated on 88 held-out examples (stratified across all 89 tools). Scoring: 1.0 = correct tool + arguments, 0.75 = correct tool + extra args, 0.5 = correct tool + wrong args, 0.0 = wrong tool or no tool call.

See RESULTS.md for full experiment history.

Limitations

Trained on synthetic data only; may not handle ambiguous real-world requests well
Tool descriptions heavily influence accuracy — the base model with good descriptions can outperform the fine-tune on some tasks
English only
Designed for single-turn or short multi-turn tool-calling; not a general chat model

Source

Developed on Radicle: rad:z2YCwgkXrZkUTu8c4CQayvk9Pkpky

License

Apache-2.0

Downloads last month: 26

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for h-d-h/rad-model

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Finetuned

unsloth/Qwen2.5-7B-Instruct

Quantized

(11)

this model

h-d-h
/

rad-model

rad-model

Intended use

Training

Serving

Evaluation

Limitations

Source

License

Model tree for h-d-h/rad-model

Dataset used to train h-d-h/rad-model