Intern-S2

About

What Intern-S2 is

Intern-S2-Preview 💻Github Repo • 🤗Model Collections • 💬Online Chat 👋 join us on <a href="https://discord.gg/xa29JuW87d" target="blank"Discord</a and <a href="https://cdn.vansin.top/intern-s1.jpg" target="blank"WeChat</a Introduction We introduce Intern-S2-Preview, an efficient 35B scientific multimodal foundation model. Beyond conventional parameter and data scaling, Intern-S2-Preview explores task scaling: increasing the difficulty, diversity, and coverage of scientific tasks to further unlock model capabilities. By extending professional scientific tasks into a full-chain training pipeline from pre-training to reinforcement learning, Intern-S2-Preview achieves performance comparable to the trillion-scale Intern-S1-Pro on multiple core professional scientific tasks, while using only 35B parameters (continued pretrained from Qwen3.5). At the same time, it maintains strong general reasoning, multimodal understanding, and agent capabilities. Features - Scientific task scaling with full-chain training. Intern-S2-Preview scales hundreds of professional scientific tasks from pre-training to RL, enabling strong performance across multiple specialized domains at only 35B parameters. It further strengthens spatial modeling for small-molecule structures and introduces real-valued prediction modules, making it the first open-source model with both material crystal structure generation capability and strong general capabilities. - Enhanced agent capabilities for scientific workflows. Intern-S2-Preview significantly improves agentic abilities over the previous generation, achieving strong results on multiple scientific agent benchmarks. - Efficient RL reasoning with MTP and CoT compression. During RL, Intern-S2-Preview adopts shared-weight MTP with KL loss to reduce the mismatch between training and inference behavior, substantially improving MTP accept rate and token generation speed. It also introduces CoT compression techniques to shorten responses while preserving strong reasoning capability, achieving improvements in both performance and efficiency. - Upgraded time-series Modeling for better physical signal representation; supports long, heterogeneous time-series (10^0

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How language models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys intern-s2 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (intern-s2 below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"intern-s2","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Licence

Open weights

Sources

Weights & code

Explore

More language models