---
title: Intern-S1-Pro
description: "Intern-S1-Pro is a trillion-parameter mixture-of-experts multimodal scientific reasoning model from Shanghai AI Laboratory (InternLM): 1T parameters in 512 experts, 22B active per token. Besides text and images it takes long time series, up to a million points."
tags:
- conversational
- custom_code
- fp8
- image-text-to-text
- interns1_pro
- multimodal
- reasoning
- scientific-llm
- text-generation
license: apache-2.0
source_url: https://huggingface.co/internlm/Intern-S1-Pro
---

# Intern-S1-Pro

> **Mirrored metadata.** This card is reproduced on Atlas for discovery. The artifact itself is not hosted here — follow the source link for the files, and refer to the upstream licence for terms of use.

Intern-S1-Pro is a trillion-parameter mixture-of-experts multimodal scientific reasoning model from Shanghai AI Laboratory (InternLM): 1T parameters in 512 experts, 22B active per token. Besides text and images it takes long time series, up to a million points.

Upstream identifier: `internlm/Intern-S1-Pro`. Paper: [arXiv:2603.25040](https://arxiv.org/abs/2603.25040).

**Source:** https://huggingface.co/internlm/Intern-S1-Pro

**Licence:** apache-2.0

_This model is part of the Atlas demo catalogue. See the repository history for provenance._