Llama 3.1 8B Instant

Meta's Llama 3.1 8B Instant model offers high-speed inference at 750 tokens per second, making it a powerful and efficient choice for a wide range of natural language processing tasks. With a 128K token context window, this model can handle long-form content and complex inputs.

Supports a 128K token context window. Handles Text, Image, Video, Audio, Transcription, Text-to-Speech inputs and outputs. Supports fine-tuning for custom applications.