Moondream
9.6kTry the model

Computer Use

Given a screenshot and an instruction like "Click on Zoom 161%," Moondream returns the point to click. Evaluated on a 1,000-sample held-out test set, the fine-tune raises click accuracy from 27.0% to 63.8%, beating GPT-5.4's 39.9%.

Start your own fine-tune

Click accuracy

BaseGPT-5.4Fine-tuned
MethodSFT
Steps1,500
Training time12 hrs 10 min
Cost$181.4

See it in action

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

Prompt

Click on "Zoom 161%"

Base Moondream 3 Preview

Presentation editor screenshot with zoom control target

GPT-5.4

Presentation editor screenshot with zoom control target

Fine-tuned Moondream 3 Preview

Presentation editor screenshot with zoom control target
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

lens = md.Lens()

# Hidden boilerplate and data code

lens.train_step(
    training_data=[
        {
            "image": example["screenshot"],
            "prompt": example["instruction"],
            "output": {
                "x": example["target_x"],
                "y": example["target_y"],
            },
        }
        for example in training_data
    ]
)

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.