Skip to main content
Ollama is experimental. Review quality is significantly lower than Claude or GPT-4o. Use only if your environment cannot make external API calls.
Ollama lets you run open-source models locally. This provider is designed for air-gapped environments where no external API access is possible.

​
When to use Ollama

  • Your network has no outbound internet access
  • Security policy prohibits sending code to external LLM APIs
  • You want to evaluate MergeWatch without any API keys

​
Configuration

Set these environment variables in your .env file or container environment:
VariableRequiredValue
LLM_PROVIDERYesollama
OLLAMA_BASE_URLNoOllama API endpoint (default: http://localhost:11434)
LLM_MODELNoOverride the default model

​
Default model

MergeWatch uses qwen2.5-coder:7b by default. This model runs on GPUs with 8 GB VRAM and provides reasonable code understanding for its size.

​
Setup

Pull the model before starting MergeWatch: 
ollama pull qwen2.5-coder:7b
Verify the model is available: 
ollama list

​
Docker Compose setup

Run Ollama as a sidecar alongside MergeWatch:
docker-compose.yml
services:
  mergewatch:
    image: ghcr.io/santthosh/mergewatch:latest
    ports:
      - "3000:3000"
    env_file: .env
    environment:
      LLM_PROVIDER: ollama
      OLLAMA_BASE_URL: http://ollama:11434
    depends_on:
      - ollama

  ollama:
    image: ollama/ollama:latest
    ports:
      - "11434:11434"
    volumes:
      - ollama-data:/root/.ollama
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]

volumes:
  ollama-data:
After starting the stack for the first time, exec into the Ollama container to pull the model:
docker compose exec ollama ollama pull qwen2.5-coder:7b

​
Hardware requirements

ComponentMinimumRecommended
GPU VRAM8 GB16 GB
System RAM16 GB32 GB
Disk10 GB free20 GB free
Larger models like qwen2.5-coder:14b produce better reviews but require 16 GB VRAM. If you have the hardware, set LLM_MODEL=qwen2.5-coder:14b for improved quality.

​
Next steps

Air-gapped deployment

Full guide for deploying MergeWatch without internet access.

Anthropic (direct)

The recommended provider for the best review quality.

Configure review behavior

Tune sensitivity, ignored paths, and review focus areas.

Environment variables

Full list of supported environment variables.