INTELLECT-3.1

INTELLECT-3.1

<div align="center"> <img src="https://huggingface.co/PrimeIntellect/INTELLECT-3/resolve/main/banner.png" alt="Prime Intellect Logo" /> </div> <p align="center"> <strong>INTELLECT-3.1: A 100B+ MoE trained with large-scale RL</strong> <br><br> Trained with <a href="https://github.com/PrimeIntellect-ai/prime-rl">prime-rl</a> and <a href="https://github.com/PrimeIntellect-ai/verifiers">verifiers</a> <br> Environments released on <a href="https://app.primeintellect.ai/dashboard/environments">Environments Hub</a> <br> Read the <a href="https://primeintellect.ai/blog/intellect-3">Blog</a> & <a href="https://storage.googleapis.com/intellect-3-paper/INTELLECT_3_Technical_Report.pdf">Technical Report</a> <br> <a href="https://x.com/primeintellect">X</a> | <a href="https://discord.gg/RC5GvMbfDf">Discord</a> | <a href="https://app.primeintellect.ai/dashboard/create-cluster">Prime Intellect Platform</a> </p>

Introduction

INTELLECT-3.1 is a 106B (A12B) parameter Mixture-of-Experts reasoning model built as a continued training of INTELLECT-3 with additional reinforcement learning on math, coding, software engineering, and agentic tasks.

Training was performed with prime-rl using environments built with the verifiers library. All training and evaluation environments are available on the Environments Hub.

The model, training frameworks, and environments are open-sourced under fully-permissive licenses (MIT and Apache 2.0).

For more details, see the technical report.

Serving with vLLM

The model can be served on 2x H200s:

vllm serve PrimeIntellect/INTELLECT-3.1 \
    --tensor-parallel-size 2 \
    --enable-auto-tool-choice \
    --tool-call-parser qwen3_coder \
    --reasoning-parser deepseek_r1

Citation

@misc{intellect3.1,
  title={INTELLECT-3.1: Technical Report},
  author={Prime Intellect Team},
  year={2025},
  url={https://huggingface.co/PrimeIntellect/INTELLECT-3.1}
}