Instructions to use ownllm/ownllm-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ownllm/ownllm-models 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 ownllm/ownllm-models:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ownllm/ownllm-models:Q4_K_M

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/ownllm/ownllm-models:Q4_K_M

LM Studio
Jan

vLLM

How to use ownllm/ownllm-models with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ownllm/ownllm-models:Q4_K_M

Ollama
How to use ownllm/ownllm-models with Ollama:
```
ollama run hf.co/ownllm/ownllm-models:Q4_K_M
```
Unsloth Desktop

How to use ownllm/ownllm-models with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ownllm/ownllm-models: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": "ownllm/ownllm-models:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ownllm/ownllm-models with Docker Model Runner:
```
docker model run hf.co/ownllm/ownllm-models:Q4_K_M
```

Lemonade

How to use ownllm/ownllm-models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ownllm/ownllm-models:Q4_K_M

Run and chat with the model

lemonade run user.ownllm-models-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use ownllm/ownllm-models with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ownllm/ownllm-models: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 ownllm/ownllm-models:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ownllm/ownllm-models with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ownllm/ownllm-models: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 "ownllm/ownllm-models: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"

OwnLLM model files

These are the model files used by OwnLLM, a free private AI assistant that runs on your own computer. They are unmodified copies of the Qwen2.5 Instruct GGUF files published by Alibaba Cloud's Qwen team under the Apache License 2.0. The largest model (7B) has been merged and re-split into four smaller pieces with llama.cpp's llama-gguf-split so it can be hosted as release files; the weights are unchanged, only the file layout differs. The Apache License 2.0 text is included as LICENSE.

OwnLLM is not affiliated with or endorsed by the Qwen team. Originals: Qwen/Qwen2.5-0.5B-Instruct-GGUF, Qwen/Qwen2.5-1.5B-Instruct-GGUF, Qwen/Qwen2.5-7B-Instruct-GGUF.

Model	File	Size	SHA-256
tiny	qwen2.5-0.5b-instruct-q4_k_m.gguf	491 MB	`74a4da8c9fdbcd15bd1f6d01d621410d31c6fc00986f5eb687824e7b93d7a9db`
small	qwen2.5-1.5b-instruct-q4_k_m.gguf	1,117 MB	`6a1a2eb6d15622bf3c96857206351ba97e1af16c30d7a74ee38970e434e9407e`
medium	qwen2.5-7b-instruct-q3_k_m.gguf	3,808 MB	`a96b16179dc6cc9afdf0cf7a96a80c199cbd00b9be207c3465be21cb721cca5e`
standard	ownllm-standard-00001-of-00004.gguf	1,451 MB	`105e76dc0cc7be79d6adb9a020597e2648a1af8b80cf7ebfc3e1761dab00d9d0`
standard	ownllm-standard-00002-of-00004.gguf	1,497 MB	`36071ff384ade003edb5ade2f78023fb305f10672dc66fdc6e576d33968e8de9`
standard	ownllm-standard-00003-of-00004.gguf	1,493 MB	`d4e33707191aceeedd1ece000c07c7d75a74b414bd2a5c517b7a1319647d9b39`
standard	ownllm-standard-00004-of-00004.gguf	243 MB	`334debaafaae76816f932dcff4a8cb18b8a896c7c1709db5cec762af3d04ba8d`