What are the hardware requirements for Intern S2 397B FP8?

Intern S2 397B FP8 requires approximately 175.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Intern S2 397B FP8 and how large is it?

Intern S2 397B FP8 is developed by internlm, a model with 397b 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 397B FP8?

Intern S2 397B FP8 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Intern S2 397B FP8 by internlm — VRAM 175.2GB

Name: Intern S2 397B FP8
Author: internlm

Intern S2 397B FP8 is an open-source language model by internlm. Features: 397b LLM, VRAM: 175.2GB, License: apache-2.0, LLM Explorer Score: 0.29.

Conversational Endpoints compatible Fp8 Image-text-to-text Qwen3 5 moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/internlm/Intern-S2-397B-FP8

Intern S2 397B FP8 Parameters and Internals

LLM Name	Intern S2 397B FP8
Repository 🤗	https://huggingface.co/internlm/Intern-S2-397B-FP8
Model Size	397b
Required VRAM	175.2 GB
Updated	2026-09-16
Maintainer	internlm
Model Type	qwen3_5_moe
Model Files	4.3 GB: 1-of-95 4.3 GB: 2-of-95 4.3 GB: 3-of-95 4.3 GB: 4-of-95 4.3 GB: 5-of-95 4.3 GB: 6-of-95 3.2 GB: 7-of-95 4.3 GB: 8-of-95 4.3 GB: 9-of-95 4.3 GB: 10-of-95 4.3 GB: 11-of-95 4.3 GB: 12-of-95 4.3 GB: 13-of-95 4.3 GB: 14-of-95 4.3 GB: 15-of-95 4.3 GB: 16-of-95 4.3 GB: 17-of-95 4.3 GB: 18-of-95 4.3 GB: 19-of-95 4.3 GB: 20-of-95 4.3 GB: 21-of-95 4.3 GB: 22-of-95 4.3 GB: 23-of-95 4.3 GB: 24-of-95 4.3 GB: 25-of-95 4.3 GB: 26-of-95 4.3 GB: 27-of-95 4.3 GB: 28-of-95 4.3 GB: 29-of-95 4.3 GB: 30-of-95 4.3 GB: 31-of-95 4.3 GB: 32-of-95 4.3 GB: 33-of-95 4.3 GB: 34-of-95 4.3 GB: 35-of-95 4.3 GB: 36-of-95 4.3 GB: 37-of-95 4.3 GB: 38-of-95 4.3 GB: 39-of-95 4.3 GB: 40-of-95 4.3 GB: 41-of-95
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Transformers Version	4.57.0.dev0

Rank the Intern S2 397B FP8 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

Best Alternatives to Intern S2 397B FP8

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.5 397B A17B	0K / 369.8 GB	331990	1549
Qwen3.5 397B A17B NVFP4	0K / 251.1 GB	428565	102
Qwen3.5 397B A17B NVFP4 V2	0K / 243.5 GB	23781	5
Ornith 1.0 397B FP8	0K / 147.7 GB	597119	183
Ornith 1.0 397B	0K / 288.5 GB	239391	262
Intern S2 397B	0K / 180.5 GB	227	44
XYZ Aquila Pro	0K / 225 GB	1805	375
Qwen3.5 397B A17B	0K / 369.8 GB	53	13
Qwen3.5 397B A17B FP8	0K / 184.9 GB	825515	182
Ornith 1.5 397B	0K / 279.9 GB	672	66

Note: green Score (e.g. "73.2") means that the model is better than internlm/Intern-S2-397B-FP8.