Running local LLMs on your own hardware is no longer the domain of the chosen few with clusters of H100s. Or is it? 😁

🗓 May 1 at 6:00 PM Moscow time there will be a live stream in «Assembly Point». We will be discussing the installation and use of local models.

What will be covered:
▪️ How to choose a suitable model for your hardware so that it doesn't eat up all system memory and works with adequate TPS (tokens per second).
▪️ Running the model in chat mode for everyday tasks.
▪️ Connecting a local LLM to an agentic IDE (using Kilo Code as an example).
▪️ Routing requests to the local model via LangChain.
▪️ Is it even necessary?

The broadcast and recording will be available to participants of the Assembly Point. Access is arranged through the bot: https://t.me/TScompiler_bot