LLM EXPLORER 56,604 MODELS INDEXED

InternVL3 5 14B Pretrained by OpenGVLab

By OpenGVLab · 31 downloads
HF Repo ↗ Copy URL

InternVL3 5 14B Pretrained is an open-source language model by OpenGVLab. Features: 14b LLM, VRAM: 30.1GB, License: apache-2.0, LLM Explorer Score: 0.2.

  Arxiv:2312.14238   Arxiv:2404.16821   Arxiv:2411.10442   Arxiv:2412.05271   Arxiv:2504.10479   Arxiv:2508.18265 Base model:merge:opengvlab/int... Base model:merge:qwen/qwen3-14... Base model:opengvlab/internvit...   Base model:qwen/qwen3-14b   Conversational   Custom code   Dataset:opengvlab/mmpr-tiny   Dataset:opengvlab/mmpr-v1.2   Feature-extraction   Image-text-to-text   Internvl   Internvl chat   Multilingual   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/OpenGVLab/InternVL3_5-14B-Pretrained 

InternVL3 5 14B Pretrained Parameters and Internals

LLM NameInternVL3 5 14B Pretrained
Repository 🤗https://huggingface.co/OpenGVLab/InternVL3_5-14B-Pretrained 
Base Model(s)  OpenGVLab/InternViT-300M-448px-V2_5   Qwen3 14B   OpenGVLab/InternViT-300M-448px-V2_5   Qwen/Qwen3-14B
Model Size14b
Required VRAM30.1 GB
Updated2026-08-08
MaintainerOpenGVLab
Model Typeinternvl_chat
Model Files  4.9 GB: 1-of-7   5.0 GB: 2-of-7   4.9 GB: 3-of-7   5.0 GB: 4-of-7   4.9 GB: 5-of-7   3.8 GB: 6-of-7   1.6 GB: 7-of-7
Model ArchitectureInternVLChatModel
Licenseapache-2.0
Model Max Length32768
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to InternVL3 5 14B Pretrained

Best Alternatives
Context / RAM
Downloads
Likes
InternVL3 5 14B0K / 30.2 GB2359931
InternVL3 5 14B Instruct0K / 30.1 GB53379
InternVL3 5 14B Flash0K / 30.9 GB3248
InternVL3 5 14B MPO0K / 30.1 GB383
InternVL3 14B Pretrained0K / 30.4 GB491
InternVL3 14B AWQ0K / 10.7 GB34147
InternVL3 14B GGUF0K / 0.7 GB7562
Note: green Score (e.g. "73.2") means that the model is better than OpenGVLab/InternVL3_5-14B-Pretrained.