AI models 1 min read

Intern-S series vs InternLM3: scientific multimodal models or a general 8B text model

Scientific multimodal models from the InternLM organisation against InternLM3-8B-Instruct, a general-purpose instruction model. Both Apache 2.0.

Scientific multimodal or general text

The Intern-S README introduces Intern-S2-397B as a multimodal foundation model for scientific intelligence and long-horizon agents. It also documents Intern-S1, built on a 235B MoE language model and a 6B vision encoder, and Intern-S1-mini with an 8B language model. For Intern-S1 the README states uses such as interpreting chemical structures, understanding protein sequences and planning compound synthesis routes.

InternLM3 is an 8-billion-parameter instruction model, InternLM3-8B-Instruct, designed for general-purpose usage and advanced reasoning. Its README describes a deep thinking mode and a normal response mode.

Licences and running them

Both repositories sit under the InternLM GitHub organisation and both state Apache 2.0: the Intern-S README says the project is released under the Apache 2.0 license, and the InternLM3 README says code and model weights are licensed under Apache-2.0.

Intern-S lists LMDeploy, vLLM and SGLang with a user guide per model. The InternLM3 README shows Transformers, LMDeploy, SGLang and Ollama examples and notes that the 8B model in 4-bit costs nearly 8GB of GPU memory.

Who should look at which

Readers working on scientific tasks that mix text with images or molecular and protein data may start with the Intern-S series.

Readers who want a single 8B instruction model for general text and a stated 8GB 4-bit memory figure may start with InternLM3. Neither model was installed or tested for this comparison.

VendorClue read the project pages for Intern-S series on 7 November 2026 and InternLM3 on 4 November 2026. Terms and releases can change, so check the current pages before you choose.

Sources

Intern-S series: intern-s1-project · Evidence: documentation · Not checked

InternLM3: internlm3-model-source · Evidence: documentation · Not checked

Next step

Tools in this guide

All AI models tools
All guides