LLM EXPLORER 56,604 MODELS INDEXED

InternVL2 5 4B by OpenGVLab

By OpenGVLab · 260192 downloads
HF Repo ↗ Copy URL

InternVL2 5 4B is an open-source language model by OpenGVLab. Features: 3b LLM, VRAM: 7.4GB, License: mit, Instruction-Based, LLM Explorer Score: 0.24.

  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/qwen2.5-3b-ins...   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_5-4B 

InternVL2 5 4B Parameters and Internals

LLM NameInternVL2 5 4B
Repository 🤗https://huggingface.co/OpenGVLab/InternVL2_5-4B 
Base Model(s)  OpenGVLab/InternViT-300M-448px-V2_5   Qwen/Qwen2.5-3B-Instruct   OpenGVLab/InternViT-300M-448px-V2_5   Qwen/Qwen2.5-3B-Instruct
Model Size3b
Required VRAM7.4 GB
Updated2026-08-01
MaintainerOpenGVLab
Model Typeinternvl_chat
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.4 GB: 2-of-2
Model ArchitectureInternVLChatModel
Licensemit
Model Max Length16384
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Torch Data Typebfloat16
Errorsreplace

Quantized Models of the InternVL2 5 4B

Model
Likes
Downloads
VRAM
InternVL2 5 4B AWQ71973 GB