AntLingAGI Open-Sources Trillion-Parameter Ling-2.6-1T Model With SGLang Support

Original post

🎉 Congrats on the release of Ling-2.6-1T, a trillion-parameter flagship for complex, real-world tasks. Day-0 support is now live in SGLang!

☑️High Inference Efficiency: MLA + Linear Attention for lower latency & VRAM ☑️ Lower Token Overhead: "Fast Thinking" cuts verbose CoT ☑️ Reliable Multi-Step Execution: SOTA on AIME26, SWE-bench, BFCL-V4, TAU2-Bench & IFBench ☑️ Production-Ready for Agents: Claude Code, OpenClaw, OpenCode & CodeBuddy

Run it now with SGLang!

Ant Ling@AntLingAGI

🚀 Ring-2.6-1T is now open source.

A trillion-scale flagship thinking model built for real-world complex tasks: Agent workflows, coding & engineering, long-horizon tasks, complex reasoning, research, and enterprise automation.

It is designed to move beyond “answering” toward

9:35 AM · May 14, 2026 · 931 Views

intern s 2

HUGGINGFACE.COVia

Intern S2

MODELSCOPE.CNVia

Intern S1

GITHUB.COMVia

chat.intern ai.org.cn

INTERN-AI.ORG.CNVia

VIEWS2.8KBOOKMARKS2

LMSYS Org@lmsysorg

🚀 Day-0 SGLang support is live for Intern-S2-Preview! This is a 35B scientific multimodal foundation model from @intern_lm 1️⃣ Scientific task scaling: hundreds of pro tasks from pre-train to RL; first open-source model w/ material crystal structure generation 2️⃣ Stronger agents: big gains on scientific agent benchmarks 3️⃣ Efficient RL: shared-weight MTP + CoT compression for faster, leaner inference

Try it on SGLang now 👇

Intern Large Models@intern_lm

🥳Introducing Intern-S2-Preview, an efficient 35B scientific multimodal foundation model. 1⃣Delivers performance comparable to the trillion-scale Intern-S1-Pro on core scientific tasks. 2⃣The first open-source model with material crystal structure generation capabilities and

40d2.8K212

LIKES21RETWEETS2REPLIES1