What are the hardware requirements for InternVL3 78B Instruct?

InternVL3 78B Instruct requires approximately 157.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed InternVL3 78B Instruct and how large is it?

InternVL3 78B Instruct is developed by OpenGVLab, a model with 78b 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 InternVL3 78B Instruct?

InternVL3 78B Instruct is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

InternVL3 78B Instruct by OpenGVLab — VRAM 157.4GB

Name: InternVL3 78B Instruct
Author: OpenGVLab

InternVL3 78B Instruct is an open-source language model by OpenGVLab. Features: 78b LLM, VRAM: 157.4GB, License: other, Instruction-Based, LLM Explorer Score: 0.19.

Arxiv:2312.14238 Arxiv:2404.16821 Arxiv:2411.10442 Arxiv:2412.05271 Arxiv:2412.09616 Arxiv:2504.10479 Base model:finetune:opengvlab/... Base model:opengvlab/internvl3... 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/InternVL3-78B-Instruct

InternVL3 78B Instruct Parameters and Internals

LLM Name	InternVL3 78B Instruct
Repository 🤗	https://huggingface.co/OpenGVLab/InternVL3-78B-Instruct
Base Model(s)	InternVL3 78B Pretrained OpenGVLab/InternVL3-78B-Pretrained
Model Size	78b
Required VRAM	157.4 GB
Updated	2026-08-10
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	1000000
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Torch Data Type	bfloat16
Errors	replace

Rank the InternVL3 78B Instruct 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 InternVL3 78B Instruct

Model	Likes	Downloads	VRAM
InternVL3 78B Instruct GGUF	4	841	2 GB

Best Alternatives to InternVL3 78B Instruct

Best Alternatives	Context / RAM	Downloads	Likes
InternVL3 78B	0K / 157.4 GB	15801	239
InternVL3 78B Instruct GGUF	0K / 2.1 GB	841	4

Note: green Score (e.g. "73.2") means that the model is better than OpenGVLab/InternVL3-78B-Instruct.