(Research only) Moondream1 is a vision language model that performs on par with models twice its size

  • Public
  • 6K runs

Run time and cost

This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 1 seconds.


Cog implementation of MoonDream1. Referenced code from the huggingface space here


1.6B parameter model built by @vikhyatk using SigLIP, Phi-1.5 and the LLaVa training dataset. The model is release for research purposes only, commercial use is not allowed.

Try it out on Huggingface Spaces! Or check out the moondream repository on GitHub for inference code and other details.

Model Parameters VQAv2 GQA VizWiz TextVQA
LLaVA-1.5 13.3B 80.0 63.3 53.6 61.3
LLaVA-1.5 7.3B 78.5 62.0 50.0 58.2
MC-LLaVA-3B 3B 64.2 49.6 24.9 38.6
LLaVA-Phi 3B 71.4 - 35.9 48.6
moondream1 1.6B 74.3 56.3 30.3 39.8