In short, no! together.ai has a number of options available for our customers that use our platform to fine-tune their models.

Serverless LoRA Inference

A selection of our models support serverless LoRA inference, which allow you to run the model directly on our platform as you would with any other serverless model. You can find a full list of supported base models in our documentation.

Run your model locally

You can also download your model through our API, and then run it locally on your system (or host it elsewhere). You can find a detailed guide for this in our documentation.