What are the hardware requirements for InternVL3 5 38B HF?

InternVL3 5 38B HF requires approximately 77 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed InternVL3 5 38B HF and how large is it?

InternVL3 5 38B HF is developed by OpenGVLab, a model with 38b 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 5 38B HF?

InternVL3 5 38B HF is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

InternVL3 5 38B HF by OpenGVLab — VRAM 77GB

Name: InternVL3 5 38B HF
Author: OpenGVLab

InternVL3 5 38B HF is an open-source language model by OpenGVLab. Features: 38b LLM, VRAM: 77GB, License: apache-2.0, LLM Explorer Score: 0.22.

Arxiv:2312.14238 Arxiv:2404.16821 Arxiv:2411.10442 Arxiv:2412.05271 Arxiv:2504.10479 Arxiv:2508.18265 Base model:finetune:opengvlab/... Base model:opengvlab/internvl3... Conversational Custom code Dataset:opengvlab/mmpr-tiny Dataset:opengvlab/mmpr-v1.2 Endpoints compatible Image-text-to-text Internvl Multilingual Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/OpenGVLab/InternVL3_5-38B-HF

InternVL3 5 38B HF Parameters and Internals

LLM Name	InternVL3 5 38B HF
Repository 🤗	https://huggingface.co/OpenGVLab/InternVL3_5-38B-HF
Base Model(s)	InternVL3 5 38B MPO OpenGVLab/InternVL3_5-38B-MPO
Model Size	38b
Required VRAM	77 GB
Updated	2026-08-08
Maintainer	OpenGVLab
Model Type	internvl
Model Files	5.0 GB: 1-of-16 4.9 GB: 2-of-16 4.9 GB: 3-of-16 5.0 GB: 4-of-16 4.9 GB: 5-of-16 4.9 GB: 6-of-16 4.9 GB: 7-of-16 4.9 GB: 8-of-16 4.9 GB: 9-of-16 4.9 GB: 10-of-16 4.9 GB: 11-of-16 4.9 GB: 12-of-16 4.9 GB: 13-of-16 4.9 GB: 14-of-16 4.9 GB: 15-of-16 3.3 GB: 16-of-16
Model Architecture	InternVLForConditionalGeneration
License	apache-2.0
Model Max Length	40960
Transformers Version	4.55.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Torch Data Type	bfloat16
Errors	replace

Rank the InternVL3 5 38B HF 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 InternVL3 5 38B HF

Best Alternatives	Context / RAM	Downloads	Likes
InternVL3 38B Hf	0K / 77.1 GB	3920	2