What are the hardware requirements for InternVL2 4B?

InternVL2 4B requires approximately 8.3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed InternVL2 4B and how large is it?

InternVL2 4B is developed by OpenGVLab, a model with 4b 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 InternVL2 4B?

InternVL2 4B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

InternVL2 4B by OpenGVLab — VRAM 8.3GB

Name: InternVL2 4B
Author: OpenGVLab

InternVL2 4B is an open-source language model by OpenGVLab. Features: 4b LLM, VRAM: 8.3GB, License: mit, Instruction-Based, LLM Explorer Score: 0.17.

Arxiv:2312.14238 Arxiv:2404.16821 Arxiv:2410.16261 Arxiv:2412.05271 Base model:merge:microsoft/phi... Base model:merge:opengvlab/int... Base model:microsoft/phi-3-min... Base model:opengvlab/internvit... Conversational Custom code Feature-extraction Image-text-to-text Instruct Internvl Internvl chat Multilingual Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/OpenGVLab/InternVL2-4B

InternVL2 4B Parameters and Internals

LLM Name	InternVL2 4B
Repository 🤗	https://huggingface.co/OpenGVLab/InternVL2-4B
Base Model(s)	InternViT 300M 448px Phi 3 Mini 128K Instruct OpenGVLab/InternViT-300M-448px microsoft/Phi-3-mini-128k-instruct
Model Size	4b
Required VRAM	8.3 GB
Updated	2026-08-10
Maintainer	OpenGVLab
Model Type	internvl_chat
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-2 3.3 GB: 2-of-2
Model Architecture	InternVLChatModel
License	mit
Model Max Length	8192
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Torch Data Type	bfloat16

Rank the InternVL2 4B 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 InternVL2 4B

Best Alternatives	Context / RAM	Downloads	Likes
InternVL3 5 4B Instruct	0K / 9.5 GB	2057	5
InternVL3 5 4B MPO	0K / 9.5 GB	44	2
Mini InternVL Chat 4B V1.5	0K / 8.3 GB	360	62

Note: green Score (e.g. "73.2") means that the model is better than OpenGVLab/InternVL2-4B.