What are the hardware requirements for InternVL3 5 241B A28B Flash?

InternVL3 5 241B A28B Flash requires approximately 199.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed InternVL3 5 241B A28B Flash and how large is it?

InternVL3 5 241B A28B Flash is developed by OpenGVLab, a model with 241b 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 InternVL3 5 241B A28B Flash?

InternVL3 5 241B A28B Flash is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

InternVL3 5 241B A28B Flash by OpenGVLab — VRAM 199.9GB

Name: InternVL3 5 241B A28B Flash
Author: OpenGVLab

InternVL3 5 241B A28B Flash is an open-source language model by OpenGVLab. Features: 241b LLM, VRAM: 199.9GB, License: apache-2.0, LLM Explorer Score: 0.21.

Arxiv:2312.14238 Arxiv:2404.16821 Arxiv:2411.10442 Arxiv:2412.05271 Arxiv:2504.10479 Arxiv:2508.18265 Base model:finetune:opengvlab/... Base model:opengvlab/internvl3... Conversational Custom code Dataset:opengvlab/mmpr-tiny Dataset:opengvlab/mmpr-v1.2 Feature-extraction Image-text-to-text Internvl Internvl chat Multilingual Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/OpenGVLab/InternVL3_5-241B-A28B-Flash

InternVL3 5 241B A28B Flash Parameters and Internals

LLM Name	InternVL3 5 241B A28B Flash
Repository 🤗	https://huggingface.co/OpenGVLab/InternVL3_5-241B-A28B-Flash
Base Model(s)	InternVL3 5 241B A28B OpenGVLab/InternVL3_5-241B-A28B
Model Size	241b
Required VRAM	199.9 GB
Updated	2026-08-08
Maintainer	OpenGVLab
Model Type	internvl_chat
Model Files	5.0 GB: 1-of-97 4.9 GB: 2-of-97 5.0 GB: 3-of-97 5.0 GB: 4-of-97 5.0 GB: 5-of-97 5.0 GB: 6-of-97 5.0 GB: 7-of-97 5.0 GB: 8-of-97 5.0 GB: 9-of-97 5.0 GB: 10-of-97 5.0 GB: 11-of-97 5.0 GB: 12-of-97 5.0 GB: 13-of-97 5.0 GB: 14-of-97 5.0 GB: 15-of-97 5.0 GB: 16-of-97 5.0 GB: 17-of-97 5.0 GB: 18-of-97 5.0 GB: 19-of-97 5.0 GB: 20-of-97 5.0 GB: 21-of-97 5.0 GB: 22-of-97 5.0 GB: 23-of-97 5.0 GB: 24-of-97 5.0 GB: 25-of-97 5.0 GB: 26-of-97 5.0 GB: 27-of-97 5.0 GB: 28-of-97 5.0 GB: 29-of-97 5.0 GB: 30-of-97 5.0 GB: 31-of-97 5.0 GB: 32-of-97 5.0 GB: 33-of-97 5.0 GB: 34-of-97 5.0 GB: 35-of-97 5.0 GB: 36-of-97 5.0 GB: 37-of-97 5.0 GB: 38-of-97 5.0 GB: 39-of-97 5.0 GB: 40-of-97
Model Architecture	InternVLChatModel
License	apache-2.0
Torch Data Type	bfloat16

Rank the InternVL3 5 241B A28B Flash 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 InternVL3 5 241B A28B Flash

Best Alternatives	Context / RAM	Downloads	Likes
InternVL3 5 241B A28B Instruct	0K / 205 GB	4886	17
InternVL3 5 241B A28B	0K / 189.1 GB	430	139
InternVL3 5 241B A28B MPO	0K / 210 GB	30	2

Note: green Score (e.g. "73.2") means that the model is better than OpenGVLab/InternVL3_5-241B-A28B-Flash.