What are the hardware requirements for InternVL2 5 2B?

InternVL2 5 2B requires approximately 4.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed InternVL2 5 2B and how large is it?

InternVL2 5 2B is developed by OpenGVLab, a model with 8b 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 5 2B?

InternVL2 5 2B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

InternVL2 5 2B by OpenGVLab — VRAM 4.4GB

Name: InternVL2 5 2B
Author: OpenGVLab

InternVL2 5 2B is an open-source language model by OpenGVLab. Features: 8b LLM, VRAM: 4.4GB, License: mit, LLM Explorer Score: 0.22.

Arxiv:2312.14238 Arxiv:2404.16821 Arxiv:2410.16261 Arxiv:2412.05271 Base model:internlm/internlm2 ... Base model:merge:internlm/inte... Base model:merge:opengvlab/int... Base model:opengvlab/internvit... Conversational Custom code Dataset:huggingfacefv/finevide... Image-feature-extraction Image-text-to-text Internvl Internvl chat Multilingual Region:us Safetensors Tensorboard

Model Card on HF 🤗: https://huggingface.co/OpenGVLab/InternVL2_5-2B

InternVL2 5 2B Parameters and Internals

LLM Name	InternVL2 5 2B
Repository 🤗	https://huggingface.co/OpenGVLab/InternVL2_5-2B
Base Model(s)	InternViT 300M 448px V2.5 Internlm2 5 1 8b Chat OpenGVLab/InternViT-300M-448px-V2_5 internlm/internlm2_5-1_8b-chat
Model Size	8b
Required VRAM	4.4 GB
Updated	2026-06-20
Maintainer	OpenGVLab
Model Type	internvl_chat
Model Files	4.4 GB
Model Architecture	InternVLChatModel
License	mit
Model Max Length	16384
Tokenizer Class	InternLM2Tokenizer
Padding Token	</s>
Torch Data Type	bfloat16

Rank the InternVL2 5 2B 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 5 2B

Best Alternatives	Context / RAM	Downloads	Likes
InternVL3 5 8B	0K / 17.1 GB	38632	102
InternVL3 8B	0K / 15.9 GB	89264	107
InternVL3 5 8B Instruct	0K / 17.1 GB	11898	17
InternVL2 2B	0K / 4.4 GB	1333840	81
SenseNova SI 1.1 InternVL3 8B	0K / 15.9 GB	112	15
InternVL3 5 8B Flash	0K / 17.6 GB	374	6
InternVL3 8B Instruct	0K / 15.9 GB	2639	13
InternVL3 5 8B MPO	0K / 17.1 GB	150	3
InternVL3 5 8B Pretrained	0K / 17.1 GB	57	2
NuExtract 2 8B	0K / 16.1 GB	1952	21

Note: green Score (e.g. "73.2") means that the model is better than OpenGVLab/InternVL2_5-2B.