Run State-of-the-art LLMs on RTX | NVIDIA NIM x AnythingLLM

Hey everyone! In this video, I'm thrilled to announce our exciting partnership with NVIDIA, showcasing their groundbreaking NIM technology paired with AnythingLLM. NVIDIA NIM provide a supercharged method to run state-of-the-art models on your RTX AI PCs, effortlessly enhancing your AI capabilities. With AnythingLLM, you can easily harness this power without any complicated setup – just bring your GPU and go! Join us as we explore NVIDIA NIM and the numerous advantages of integrating this cutting-edge technology with AnythingLLM. Discover how you can run powerful LLMs entirely on your local hardware, optimizing your AI inference and workflows like never before. AnythingLLM Docs https://docs.anythingllm.com/nvidia-nims/introduction Available NIM models: https://build.nvidia.com/search?q=chat-run-on-rtx NVIDIA NIM Developer Docs: TBD CHAPTERS 0:00 Introduction 1:00 What is NVIDIA NIM? 2:11 CES 2025 Announcement 3:14 What NIMs are available today? 4:18 Lets run a NIM on a 4090 5:00 NVIDIA NIM set up in AnythingLLM 6:40 Choosing your preferred LLM 8:00 Pulling in a model 8:30 Starting a NIM for inference 9:50 Lets use the model for chats, agents, and more! 13:00 Running Deepseek-R1 15:55 Summary of NVIDIA NIM w/AnythingLLM 16:30 Thanking everyone for supporting AnythingLLM