What are the hardware requirements for InternVL2 26B AWQ?

InternVL2 26B AWQ requires approximately 23.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

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

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

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

InternVL2 26B AWQ by OpenGVLab — VRAM 23.6GB

Name: InternVL2 26B AWQ
Author: OpenGVLab

InternVL2 26B AWQ is an open-source language model by OpenGVLab. Features: 26b LLM, VRAM: 23.6GB, License: mit, Quantized, LLM Explorer Score: 0.14.

Arxiv:2306.00978 Arxiv:2312.14238 Arxiv:2404.16821 Arxiv:2410.16261 Arxiv:2412.05271 Awq Base model:opengvlab/internvl2... Base model:quantized:opengvlab... Conversational Custom code Feature-extraction Image-text-to-text Internvl Internvl chat Multilingual Pytorch Quantized Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/OpenGVLab/InternVL2-26B-AWQ

InternVL2 26B AWQ Parameters and Internals

LLM Name	InternVL2 26B AWQ
Repository 🤗	https://huggingface.co/OpenGVLab/InternVL2-26B-AWQ
Base Model(s)	InternVL2 26B OpenGVLab/InternVL2-26B
Model Size	26b
Required VRAM	23.6 GB
Updated	2026-08-08
Maintainer	OpenGVLab
Model Type	internvl_chat
Model Files	2.0 GB: 1-of-13 2.0 GB: 2-of-13 2.0 GB: 3-of-13 2.0 GB: 4-of-13 2.0 GB: 5-of-13 1.2 GB: 6-of-13 2.0 GB: 7-of-13 2.0 GB: 8-of-13 2.0 GB: 9-of-13 2.0 GB: 10-of-13 2.0 GB: 11-of-13 1.0 GB: 12-of-13 1.4 GB: 13-of-13
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	InternVLChatModel
License	mit
Model Max Length	8192
Tokenizer Class	InternLM2Tokenizer
Padding Token	</s>
Torch Data Type	float16

Rank the InternVL2 26B AWQ 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 26B AWQ

Best Alternatives	Context / RAM	Downloads	Likes
InternVL2 5 26B AWQ	0K / 23.6 GB	1691	10
InternVL2 5 26B MPO AWQ	0K / 23.6 GB	128	4
InternVL2 5 26B MPO	0K / 51.2 GB	142	14

Note: green Score (e.g. "73.2") means that the model is better than OpenGVLab/InternVL2-26B-AWQ.