LLM EXPLORER 56,604 MODELS INDEXED

InternVL3 8B Pretrained by OpenGVLab

By OpenGVLab · 35 downloads
HF Repo ↗ Copy URL

InternVL3 8B Pretrained is an open-source language model by OpenGVLab. Features: 7b LLM, VRAM: 15.9GB, License: apache-2.0, LLM Explorer Score: 0.18.

  Arxiv:2312.14238   Arxiv:2404.16821   Arxiv:2411.10442   Arxiv:2412.05271   Arxiv:2412.09616   Arxiv:2504.10479 Base model:merge:opengvlab/int... Base model:merge:qwen/qwen2.5-... Base model:opengvlab/internvit...   Base model:qwen/qwen2.5-7b   Conversational   Custom code   Feature-extraction   Image-text-to-text   Internvl   Internvl chat   Multilingual   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/OpenGVLab/InternVL3-8B-Pretrained 

InternVL3 8B Pretrained Parameters and Internals

LLM NameInternVL3 8B Pretrained
Repository 🤗https://huggingface.co/OpenGVLab/InternVL3-8B-Pretrained 
Base Model(s)  OpenGVLab/InternViT-300M-448px-V2_5   Qwen/Qwen2.5-7B   OpenGVLab/InternViT-300M-448px-V2_5   Qwen/Qwen2.5-7B
Model Size7b
Required VRAM15.9 GB
Updated2026-08-08
MaintainerOpenGVLab
Model Typeinternvl_chat
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 ArchitectureInternVLChatModel
Licenseapache-2.0
Model Max Length1000000
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to InternVL3 8B Pretrained

Best Alternatives
Context / RAM
Downloads
Likes
InternVL2 8B0K / 16.1 GB114916186
InternVL2 5 8B0K / 16.1 GB17080105
Note: green Score (e.g. "73.2") means that the model is better than OpenGVLab/InternVL3-8B-Pretrained.