DeepSeek's New AI Speed Hack Is Amazing

❤️ Check out Lambda here and sign up for their GPU Cloud: https://ift.tt/2XrhLDA 📝 The DeepSeek paper is available here: https://ift.tt/0TItgYp 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Adam Bridges, Benji Rabhan, B Shang, Cameron Navor, Charles Ian Norman Venn, Christian Ahlin, Eric T, Fred R, Gordon Child, Juan Benet, Michael Tedder, Owen Skarpness, Richard Sundvall, Ryan Stankye, Shawn Becker, Steef, Taras Bobrovytsky, Tazaur Sagenclaw, Tybie Fitzhugh, Ueli Gallizzi

Efficient models only pay off if your hardware can serve them. If you are picking a card for local inference, this guide to the best GPUs for running LLMs locally covers it in detail. Watch next: Ollama Tutorial | Run Llama2 locally | 7 billion parameter model | No GPU | LangChain Integration.