Create, run, and share portable large language models (LLMs). Ollama bundles a model’s weights, configuration, prompts, and more into self-contained packages that can run on any machine.
### Portable Large Language Models (LLMs)
Package models as a series of layers in a portable, easy to manage format.
#### The idea behind Ollama
- Universal model format that can run anywhere: desktop, cloud servers & other devices.
- Encapsulate everything a model needs to operate – weights, configuration, and data – into a single package.
- Build custom models from base models like Meta's [Llama 2](https://ai.meta.com/llama/)
- Share large models without having to transmit large amounts of data.
This format is inspired by the [image spec](https://github.com/opencontainers/image-spec) originally introduced by Docker for Linux containers. Ollama extends this format to package large language models.
To run and chat with [Llama 2](https://ai.meta.com/llama), the new model by Meta:
```
ollama run llama2
```
## Model library
Ollama includes a library of open-source, pre-trained models. More models are coming soon. You should have at least 8 GB of RAM to run the 3B models, 16 GB to run the 7B models, and 32 GB to run the 13B models.
