What are the hardware requirements for InternVL3 5 30B A3B Pretrained?

InternVL3 5 30B A3B Pretrained requires approximately 49.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed InternVL3 5 30B A3B Pretrained and how large is it?

InternVL3 5 30B A3B Pretrained is developed by OpenGVLab, a model with 30b 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 30B A3B Pretrained?

InternVL3 5 30B A3B Pretrained is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

InternVL3 5 30B A3B Pretrained by OpenGVLab — VRAM 49.2GB

Name: InternVL3 5 30B A3B Pretrained
Author: OpenGVLab

InternVL3 5 30B A3B Pretrained is an open-source language model by OpenGVLab. Features: 30b LLM, VRAM: 49.2GB, License: apache-2.0, LLM Explorer Score: 0.19.

Arxiv:2312.14238 Arxiv:2404.16821 Arxiv:2411.10442 Arxiv:2412.05271 Arxiv:2504.10479 Arxiv:2508.18265 Base model:merge:opengvlab/int... Base model:merge:qwen/qwen3-30... Base model:opengvlab/internvit... Base model:qwen/qwen3-30b-a3b 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_5-30B-A3B-Pretrained

InternVL3 5 30B A3B Pretrained Parameters and Internals

LLM Name	InternVL3 5 30B A3B Pretrained
Repository 🤗	https://huggingface.co/OpenGVLab/InternVL3_5-30B-A3B-Pretrained
Base Model(s)	InternViT 300M 448px V2.5 Qwen3 30B A3B OpenGVLab/InternViT-300M-448px-V2_5 Qwen/Qwen3-30B-A3B
Model Size	30b
Required VRAM	49.2 GB
Updated	2026-08-08
Maintainer	OpenGVLab
Model Type	internvl_chat
Model Files	1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1 1.2 GB: 0-of-1
Model Architecture	InternVLChatModel
License	apache-2.0
Torch Data Type	bfloat16

Rank the InternVL3 5 30B A3B Pretrained 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 30B A3B Pretrained

Best Alternatives	Context / RAM	Downloads	Likes
InternVL3 5 30B A3B	0K / 61.7 GB	110268	43
InternVL3 5 30B A3B Flash	0K / 62.2 GB	332	7
InternVL3 5 30B A3B Instruct	0K / 49.2 GB	418	11
InternVL3 5 30B A3B MPO	0K / 50.4 GB	48	4

Note: green Score (e.g. "73.2") means that the model is better than OpenGVLab/InternVL3_5-30B-A3B-Pretrained.