What are the hardware requirements for InternVL3 8B?

InternVL3 8B requires approximately 15.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed InternVL3 8B and how large is it?

InternVL3 8B 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 InternVL3 8B?

InternVL3 8B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

InternVL3 8B by OpenGVLab — VRAM 15.9GB

Name: InternVL3 8B
Author: OpenGVLab

InternVL3 8B is an open-source language model by OpenGVLab. Features: 8b LLM, VRAM: 15.9GB, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.25.

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 Dataset:opengvlab/mmpr-v1.2 Feature-extraction Image-text-to-text Instruct Internvl Internvl chat Multilingual Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/OpenGVLab/InternVL3-8B

InternVL3 8B Parameters and Internals

LLM Name	InternVL3 8B
Repository 🤗	https://huggingface.co/OpenGVLab/InternVL3-8B
Base Model(s)	InternVL3 8B Instruct OpenGVLab/InternVL3-8B-Instruct
Model Size	8b
Required VRAM	15.9 GB
Updated	2026-07-20
Maintainer	OpenGVLab
Model Type	internvl_chat
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-4 5.0 GB: 2-of-4 4.8 GB: 3-of-4 1.1 GB: 4-of-4
Model Architecture	InternVLChatModel
License	apache-2.0
Model Max Length	12288
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Torch Data Type	bfloat16
Errors	replace

Rank the InternVL3 8B 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 8B

Model	Likes	Downloads	VRAM
InternVL3 8B GGUF	6	2401	0 GB
InternVL3 8B AWQ	8	452	6 GB

Best Alternatives to InternVL3 8B

Best Alternatives	Context / RAM	Downloads	Likes
InternVL3 5 8B Instruct	0K / 17.1 GB	11898	17
InternVL3 8B Instruct	0K / 15.9 GB	2639	13
InternVL3 5 8B MPO	0K / 17.1 GB	150	3
InternVL3 9B Pretrained	0K / 18.3 GB	24	0
InternVL3 8B Instruct GGUF	0K / 0.7 GB	642	4