What are the hardware requirements for Intern S1 Pro BF16?

Intern S1 Pro BF16 requires approximately 456 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Intern S1 Pro BF16 and how large is it?

Intern S1 Pro BF16 is developed by internlm, a model with 917b 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 S1 Pro BF16?

Intern S1 Pro BF16 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Intern S1 Pro BF16 by internlm — VRAM 456GB

Name: Intern S1 Pro BF16
Author: internlm

Intern S1 Pro BF16 is an open-source language model by internlm. Features: 917b LLM, VRAM: 456GB, License: apache-2.0, LLM Explorer Score: 0.23.

Arxiv:2508.15763 Arxiv:2603.25040 Conversational Custom code Image-text-to-text Interns1 pro Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/internlm/Intern-S1-Pro-BF16

Intern S1 Pro BF16 Parameters and Internals

LLM Name	Intern S1 Pro BF16
Repository 🤗	https://huggingface.co/internlm/Intern-S1-Pro-BF16
Model Size	917b
Required VRAM	456 GB
Updated	2026-08-08
Maintainer	internlm
Model Type	interns1_pro
Model Files	12.0 GB: 1-of-153 12.0 GB: 2-of-153 12.0 GB: 3-of-153 12.0 GB: 4-of-153 12.0 GB: 5-of-153 12.0 GB: 6-of-153 12.0 GB: 7-of-153 12.0 GB: 8-of-153 12.0 GB: 9-of-153 12.0 GB: 10-of-153 12.0 GB: 11-of-153 12.0 GB: 12-of-153 12.0 GB: 13-of-153 12.0 GB: 14-of-153 12.0 GB: 15-of-153 12.0 GB: 16-of-153 12.0 GB: 17-of-153 12.0 GB: 18-of-153 12.0 GB: 19-of-153 12.0 GB: 20-of-153 12.0 GB: 21-of-153 12.0 GB: 22-of-153 12.0 GB: 23-of-153 12.0 GB: 24-of-153 12.0 GB: 25-of-153 12.0 GB: 26-of-153 12.0 GB: 27-of-153 12.0 GB: 28-of-153 12.0 GB: 29-of-153 12.0 GB: 30-of-153 12.0 GB: 31-of-153 12.0 GB: 32-of-153 12.0 GB: 33-of-153 12.0 GB: 34-of-153 12.0 GB: 35-of-153 12.0 GB: 36-of-153 12.0 GB: 37-of-153 12.0 GB: 38-of-153
Model Architecture	InternS1ProForConditionalGeneration
License	apache-2.0
Transformers Version	4.57.0.dev0

Rank the Intern S1 Pro BF16 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