What are the hardware requirements for Intern S2 Mobius?

Intern S2 Mobius requires approximately 72.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Intern S2 Mobius and how large is it?

Intern S2 Mobius is developed by internlm, a model with 36b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Intern S2 Mobius?

Intern S2 Mobius is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Intern S2 Mobius by internlm — VRAM 72.9GB

Name: Intern S2 Mobius
Author: internlm

Intern S2 Mobius is an open-source language model by internlm. Features: 36b LLM, VRAM: 72.9GB, License: apache-2.0, LLM Explorer Score: 0.35.

Conversational Custom code Image-text-to-text Interns2 mobius Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/internlm/Intern-S2-Mobius

Intern S2 Mobius Parameters and Internals

LLM Name	Intern S2 Mobius
Repository 🤗	https://huggingface.co/internlm/Intern-S2-Mobius
Model Size	36b
Required VRAM	72.9 GB
Updated	2026-08-09
Maintainer	internlm
Model Type	interns2_mobius
Model Files	8.5 GB: 1-of-5 16.1 GB: 2-of-5 16.1 GB: 3-of-5 16.1 GB: 4-of-5 16.1 GB: 5-of-5
Model Architecture	InternS2MobiusForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	5.2.0
Tokenizer Class	InternS1Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Intern S2 Mobius capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation