Image + text

Molmo

Fully open vision models from Ai2 (weights and data). They can point to a spot in an image and count objects; Molmo2 understands video, MolmoWeb controls a browser.

Developer
Ai2 (Allen Institute for AI), USA
First release
Sep 2024
Latest release
Mar 2026
Sizes
1B-A7B – 72B
License
Commercial use allowedApache 2.0
Russian
Not supported
Running
On your own serverNeeds a GPU
Industries
Science and research, Manufacturing and logistics
Deploy on your server Hugging Face GitHub

What it does

  • Counting products and objects in photos
  • Pointing to where an item is in an image
  • Video analysis
  • An agent that works with websites (MolmoWeb)

Where it is used

Warehousing and retailManufacturingResearch teams

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
fits

Versions

  1. MolmoPoint и MolmoWeb
  2. Molmo2 4B / 8B
  3. Molmo 7B / 72B и MolmoE-1B

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can Molmo be used in a commercial project?

Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Molmo need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Molmo support Russian?

No. The model card lists its languages and Russian is not among them.

Where can I download Molmo and what does it cost?

The Molmo weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Image + textQwen-VLAlibaba (Qwen team) · ChinaCommercial use allowed

One of the strongest open vision models: reads documents, tables, charts and video, and works with user interfaces. Since Qwen3.5, vision is built directly into the main Qwen model.

DetailsImage + textMoondreamMoondream (M87 Labs) · USACommercial use with conditions

A small, fast vision model for product use cases: answering questions, finding and pointing to objects, captions. Moondream 3.1 is a 9B MoE with 2B active.

DetailsRoboticsMolmoActAi2 (Allen Institute for AI) · USACommercial use allowed

A fully open robot control model that first "reasons" about space and trajectory, then acts. Its reasoning can be checked.

Details

Source: huggingface.co/allenai/MolmoWeb-8B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.