What are the hardware requirements for InternVL2 5 78B?

InternVL2 5 78B requires approximately 157.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed InternVL2 5 78B and how large is it?

InternVL2 5 78B 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 78B?

InternVL2 5 78B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

InternVL2 5 78B by OpenGVLab — VRAM 157.4GB

Name: InternVL2 5 78B
Author: OpenGVLab

InternVL2 5 78B is an open-source language model by OpenGVLab. Features: 6b LLM, VRAM: 157.4GB, License: other, Instruction-Based, LLM Explorer Score: 0.18.

Arxiv:2312.14238 Arxiv:2404.16821 Arxiv:2410.16261 Arxiv:2412.05271 Base model:merge:opengvlab/int... Base model:merge:qwen/qwen2.5-... Base model:opengvlab/internvit... Base model:qwen/qwen2.5-72b-in... Conversational Custom code Dataset:huggingfacefv/finevide... Feature-extraction Image-text-to-text Instruct Internvl Internvl chat Multilingual Region:us Safetensors Sharded Tensorboard Tensorflow

Model Card on HF 🤗: https://huggingface.co/OpenGVLab/InternVL2_5-78B

InternVL2 5 78B Parameters and Internals

LLM Name	InternVL2 5 78B
Repository 🤗	https://huggingface.co/OpenGVLab/InternVL2_5-78B
Base Model(s)	OpenGVLab/InternViT-6B-448px-V2_5 Qwen/Qwen2.5-72B-Instruct OpenGVLab/InternViT-6B-448px-V2_5 Qwen/Qwen2.5-72B-Instruct
Model Size	6b
Required VRAM	157.4 GB
Updated	2026-08-08
Maintainer	OpenGVLab
Model Type	internvl_chat
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-33 4.9 GB: 2-of-33 4.9 GB: 3-of-33 4.8 GB: 4-of-33 4.8 GB: 5-of-33 5.0 GB: 6-of-33 4.8 GB: 7-of-33 4.8 GB: 8-of-33 4.8 GB: 9-of-33 5.0 GB: 10-of-33 4.8 GB: 11-of-33 4.8 GB: 12-of-33 4.8 GB: 13-of-33 5.0 GB: 14-of-33 4.8 GB: 15-of-33 4.8 GB: 16-of-33 4.8 GB: 17-of-33 5.0 GB: 18-of-33 4.8 GB: 19-of-33 4.8 GB: 20-of-33 4.8 GB: 21-of-33 5.0 GB: 22-of-33 4.8 GB: 23-of-33 4.8 GB: 24-of-33 4.8 GB: 25-of-33 5.0 GB: 26-of-33 4.8 GB: 27-of-33 4.8 GB: 28-of-33 4.8 GB: 29-of-33 5.0 GB: 30-of-33 4.8 GB: 31-of-33 4.0 GB: 32-of-33 2.8 GB: 33-of-33
Model Architecture	InternVLChatModel
License	other
Model Max Length	16384
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Torch Data Type	bfloat16
Errors	replace

Rank the InternVL2 5 78B 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 78B

Model	Likes	Downloads	VRAM
InternVL2 5 78B AWQ	14	105	52 GB

Best Alternatives to InternVL2 5 78B

Best Alternatives	Context / RAM	Downloads	Likes
InternVL2 5 38B	0K / 77.1 GB	3235	49

Note: green Score (e.g. "73.2") means that the model is better than OpenGVLab/InternVL2_5-78B.