# 128K long-context reasoning

Llama-3.3-Nemotron-Super-49B-v1-FP8 is a large language model derived from Meta Llama-3.3-70B-Instruct, optimized to enhance reasoning capabilities, conversational preferences, and task execution, supporting a context length of 128K tokens.

Llama-3.1-Nemotron-Ultra-253B-CPT-v1 is a large language model based on Meta Llama-3.1-405B-Instruct, supporting 128K tokens context length, optimized through Neural Architecture Search to achieve a good balance between accuracy and efficiency.

Llama-3.3-Nemotron-Super-49B-v1 is a large language model based on Meta Llama-3.3-70B-Instruct, specializing in reasoning, conversational preferences, and task execution, supporting 128K tokens context length.

Phi-3.5-mini is a lightweight, state-of-the-art open-source model built on the dataset used by Phi-3, supporting a 128K context length with a special focus on high-quality, reasoning-rich data.