Ollama is an open-source project that lets you run lots of LLM models locally on your device, like Llama3, phi3, wizardlm2, mistral, gemma, and more.
You can easily configure the models on TypingMind using the local server of Ollama.
Watch this tutorial to see exactly how to set it up.
Chat with any AI models at: www.typingmind.com/?ref=youtube
TypingMind for teams: custom.typingmind.com/?ref=yo...