Instructions to use aelgendy/QModel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

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

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/aelgendy/QModel:Q4_K_M

LM Studio
Jan
Ollama
How to use aelgendy/QModel with Ollama:
```
ollama run hf.co/aelgendy/QModel:Q4_K_M
```

Unsloth Studio

How to use aelgendy/QModel 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 aelgendy/QModel 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 aelgendy/QModel to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for aelgendy/QModel to start chatting

How to use aelgendy/QModel with Pi:

Start the llama.cpp server

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

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": "aelgendy/QModel:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use aelgendy/QModel with OpenClaw:

Start the llama.cpp server

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

Docker Model Runner
How to use aelgendy/QModel with Docker Model Runner:
```
docker model run hf.co/aelgendy/QModel:Q4_K_M
```

Lemonade

How to use aelgendy/QModel with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull aelgendy/QModel:Q4_K_M

Run and chat with the model

lemonade run user.QModel-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use aelgendy/QModel with Hermes Agent:

Start the llama.cpp server

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

Run Hermes

hermes

Atomic Chat

QModel / docker-compose.yml

aelgendy

Sync codebase with local main (config, README, docker, gitignore updates)

15f1210 verified 8 days ago

Raw

History Blame Contribute Delete

2.34 kB

	# QModel Docker Compose Configuration — production-safe base
	# ============================================================
	# This base file is safe to deploy as-is: it does NOT bind-mount the repo,
	# so the image's own code is what runs. It ships with just the two data
	# files mounted read-only (they're excluded from the built image via
	# .dockerignore since they're large binaries that shouldn't bloat it or
	# require a rebuild every time the dataset changes).
	#
	# For local development with live code reload, `docker-compose.override.yml`
	# is picked up automatically and adds a full bind-mount on top of this.
	#
	# Configure via .env file:
	# LLM_BACKEND=ollama (default: local Ollama on host machine)
	# LLM_BACKEND=hf (HuggingFace backend)
	#
	# Usage:
	# docker-compose up # Dev (uses override.yml automatically)
	# docker-compose -f docker-compose.yml up -d # Prod (base file only, no bind-mount)
	# docker-compose logs -f # View logs
	# docker-compose down # Stop services

	services:
	qmodel:
	build: .
	container_name: qmodel-api
	ports:
	- "8000:8000"
	env_file:
	- .env
	environment:
	# Pass through HF token if using HuggingFace backend
	- HF_TOKEN=${HF_TOKEN:-}
	# Ollama host: override .env to use Docker host IP for container-to-host access
	- OLLAMA_HOST=http://host.docker.internal:11434
	volumes:
	# Data files: read-only, so a data update doesn't require an image rebuild
	- ./QModel.index:/app/QModel.index:ro
	- ./metadata.json:/app/metadata.json:ro
	# Cache HuggingFace models to avoid re-downloading
	- huggingface_cache:/root/.cache/huggingface
	# Restart automatically if container exits
	restart: on-failure:5
	extra_hosts:
	# Allow container to reach host.docker.internal on Mac/Windows
	- "host.docker.internal:host-gateway"
	networks:
	- qmodel-network
	# Health check for orchestration — /health returns 503 until ready
	healthcheck:
	test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
	interval: 30s
	timeout: 10s
	retries: 3
	start_period: 60s

	networks:
	qmodel-network:
	driver: bridge

	volumes:
	# Persistent cache for HuggingFace models
	huggingface_cache: