Llama-3.1-405B-FP8 is the FP8-quantized version of Meta's flagship 405 billion parameter Llama 3.1 model. It offers near full-precision performance while significantly reducing memory requirements, making the largest open model more accessible for inference. The model supports advanced text generation, multilingual tasks, and coding capabilities and is distributed on Hugging Face under a permissive license.
In the Foundation models & chat space, Llama 3.1 405B takes a focused approach. It focuses on delivering state-of-the-art open-source LLM performance at the frontier 405B scale with reduced precision for easier deployment. Llama 3.1 405B is an open-source project aimed at developers. The project is open source (Open Source). It runs on the web, the command line, and API.
Behind Llama 3.1 405B is Meta, based in the United States, and it first shipped in 2024. The project is developed in the open on GitHub with 7.7k stars. PulseGate's similarity index places it among 6 comparable projects. Among its 3 catalogued features are Large Language Model, Text Generation, and Multilingual Support.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do