What are the hardware requirements for InternVL2 5 26B?

InternVL2 5 26B requires approximately 51.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed InternVL2 5 26B and how large is it?

InternVL2 5 26B is developed by OpenGVLab, a model with 6b 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 26B?

InternVL2 5 26B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

InternVL2 5 26B by OpenGVLab — VRAM 51.2GB

Name: InternVL2 5 26B
Author: OpenGVLab

InternVL2 5 26B is an open-source language model by OpenGVLab. Features: 6b LLM, VRAM: 51.2GB, License: mit, LLM Explorer Score: 0.17.

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... Feature-extraction Image-text-to-text Internvl Internvl chat Multilingual Region:us Safetensors Sharded Tensorboard Tensorflow

Model Card on HF 🤗: https://huggingface.co/OpenGVLab/InternVL2_5-26B

InternVL2 5 26B Parameters and Internals

LLM Name	InternVL2 5 26B
Repository 🤗	https://huggingface.co/OpenGVLab/InternVL2_5-26B
Base Model(s)	OpenGVLab/InternViT-6B-448px-V2_5 Internlm2 5 20B Chat OpenGVLab/InternViT-6B-448px-V2_5 internlm/internlm2_5-20b-chat
Model Size	6b
Required VRAM	51.2 GB
Updated	2026-08-08
Maintainer	OpenGVLab
Model Type	internvl_chat
Model Files	5.0 GB: 1-of-11 4.9 GB: 2-of-11 4.8 GB: 3-of-11 4.9 GB: 4-of-11 4.9 GB: 5-of-11 5.0 GB: 6-of-11 5.0 GB: 7-of-11 4.9 GB: 8-of-11 5.0 GB: 9-of-11 5.0 GB: 10-of-11 1.8 GB: 11-of-11
Model Architecture	InternVLChatModel
License	mit
Model Max Length	16384
Tokenizer Class	InternLM2Tokenizer
Padding Token	</s>
Torch Data Type	bfloat16

Rank the InternVL2 5 26B 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

Quantized Models of the InternVL2 5 26B

Model	Likes	Downloads	VRAM
InternVL2 5 26B AWQ	10	1691	23 GB

Best Alternatives to InternVL2 5 26B

Best Alternatives	Context / RAM	Downloads	Likes
...ternVL3 5 241B A28B Pretrained	0K / 205 GB	36	1
InternVL3 5 38B Pretrained	0K / 77 GB	30	2
InternVL2 5 38B	0K / 77.1 GB	3235	49
InternVL2 5 78B	0K / 157.4 GB	736	193
InternVL3 78B Pretrained	0K / 157.4 GB	35	1
InternVL3 38B Pretrained	0K / 77.1 GB	34	1
InternVL Chat V1.5	0K / 51.2 GB	7921	417
InternVL2 26B	0K / 51.2 GB	1623	118
InternVL2 Llama3 76B	0K / 153.4 GB	510	213
InternVL2 40B	0K / 80.5 GB	546	93

Note: green Score (e.g. "73.2") means that the model is better than OpenGVLab/InternVL2_5-26B.