Moondream
9.6kTry the model

Aerial Airplane Spotting

Given aerial images of airports, point out each airplane. The base Moondream tends to mistake helicopters, cars, and dirt for airplanes. After RL fine-tuning Moondream's F1 score improves from 29.5% to 55.1%, while GPT-5.4 achieves only 10.1%.

Start your own fine-tune

F1

BaseGPT-5.4Fine-tuned
MethodRL
Steps148
Training time1 hr 14 min
Cost$42.24

See it in action

Switch between benchmark examples to compare the base model against the fine-tuned model on the same task.

Prompt

airplanes

Base Moondream 3 Preview

Aerial airport with dispersed aircraft

Fine-tuned Moondream 3 Preview

Aerial airport with dispersed aircraft
CorrectFalse positive

Perfection in 3 steps

1

Bring examples.

Collect images for the task you want Moondream to learn.

2

Fine-tune.

Teach Moondream with SFT or RL. Pass your data to the API and we handle the rest.

3

Deploy.

Use your model through the API or run it locally with Photon.

What is fine-tuning?

Moondream starts as a general model trained on broad, public information. Fine-tuning makes it great at one specific task by teaching it the products, documents, categories, or internal information that matter to your business.

Who is this for?

This is for teams putting vision AI into production. If you already know the task and need the model to master that job, fine-tuning is how you get there. It is built for teams that need frontier performance at real-time speed.

See the code

Fine-tuning is just a small API loop: format your data, call `train_step`, and the model updates as you go.

import moondream as md

# Create fine-tune
ft = md.ft(
    api_key="your-api-key",
    name="Aerial Airplane Spotting",
    rank=16,
)

# Hidden boilerplate and data code

requests = (
    (
        example,
        {
            "skill": "point",
            "image": example["image"],
            "object": "airplanes",
            "num_rollouts": 4,
        },
    )
    for example in training_data
)

for context, response in ft.rollout_stream(requests):
    rewards = compute_rewards(context, response)
    ft.train_step([{
        "mode": "rl",
        "request": response["request"],
        "rollouts": response["rollouts"],
        "rewards": rewards,
    }])

Frequently asked questions

Ready to take Moondream to production?

Get started

Start with the docs and run your first experiment in a few API calls.

Start fine-tuning

Need help? We'll build it for you.

We can help define the task, prepare the data, run training, validate results, and hand off a model your team can use.