LLM EXPLORER 56,604 MODELS INDEXED

InternVL2 5 38B by OpenGVLab

By OpenGVLab · 3235 downloads
HF Repo ↗ Copy URL

InternVL2 5 38B is an open-source language model by OpenGVLab. Features: 6b LLM, VRAM: 77.1GB, License: mit, Instruction-Based, LLM Explorer Score: 0.18.

  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/qwen2.5-32b-in...   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_5-38B 

InternVL2 5 38B Parameters and Internals

LLM NameInternVL2 5 38B
Repository 🤗https://huggingface.co/OpenGVLab/InternVL2_5-38B 
Base Model(s)  OpenGVLab/InternViT-6B-448px-V2_5   Qwen/Qwen2.5-32B-Instruct   OpenGVLab/InternViT-6B-448px-V2_5   Qwen/Qwen2.5-32B-Instruct
Model Size6b
Required VRAM77.1 GB
Updated2026-08-08
MaintainerOpenGVLab
Model Typeinternvl_chat
Instruction-BasedYes
Model Files  5.0 GB: 1-of-16   4.9 GB: 2-of-16   4.8 GB: 3-of-16   4.9 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   3.6 GB: 16-of-16
Model ArchitectureInternVLChatModel
Licensemit
Model Max Length16384
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Torch Data Typebfloat16
Errorsreplace

Quantized Models of the InternVL2 5 38B

Model
Likes
Downloads
VRAM
InternVL2 5 38B AWQ94730 GB

Best Alternatives to InternVL2 5 38B

Best Alternatives
Context / RAM
Downloads
Likes
InternVL2 5 78B0K / 157.4 GB736193