Image + text

LLaVA

The open project that started the trend for image-plus-text models. The OneVision line understands photos, documents and video; training data and recipes are open.

Developer
LLaVA / LMMs-Lab (researchers from the USA and China), USA / China
First release
Apr 2023
Latest release
May 2026
Sizes
0.5B – 72B
License
Commercial use allowedNewer OneVision versions: Apache 2.0; the first LLaVA models on Llama and Vicuna inherit their licenses
Russian
Not supported
Ready-made builds
GGUF, MLX (Apple)
Running
Available in OllamaAlso runs without a GPU
Industries
Science and research, Retail and marketplaces
Deploy on your server Hugging Face GitHub

What it does

  • Answering questions about photos and screenshots
  • Describing products from a photo
  • Frame-by-frame video analysis
  • A base for fine-tuning your own vision model

Where it is used

E-commerceResearch teamsContent moderation

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. LLaVA-OneVision-2-8B
  2. LLaVA-OneVision-1.5
  3. LLaVA-OneVision
  4. LLaVA-NeXT (1.6)
  5. LLaVA-1.5
  6. LLaVA

How to run it

With Ollama — the fastest wayInstall Ollama on your computer or server and find the model in its library by name. Good enough to try the model on your own tasks in one evening.Find it in the Ollama library
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. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can LLaVA be used in a commercial project?

Yes. License: Newer OneVision versions: Apache 2.0; the first LLaVA models on Llama and Vicuna inherit their licenses. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does LLaVA need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does LLaVA support Russian?

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

Where can I download LLaVA and what does it cost?

The LLaVA 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 + textInternVLShanghai AI Laboratory (OpenGVLab) · ChinaCommercial use allowed

A large family of Chinese vision models sized from 1B to 241B. InternVL-U (4B) combines image understanding, generation and editing.

DetailsImage + textMolmoAi2 (Allen Institute for AI) · USACommercial use allowed

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.

Details

Source: huggingface.co/lmms-lab-encoder/LLaVA-OneVision-2-8B-Instruct. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.