LLM EXPLORER 56,604 MODELS INDEXED

InternVL3 5 GPT OSS 20B A4B Preview HF by OpenGVLab

By OpenGVLab · 11327 downloads
HF Repo ↗ Copy URL

InternVL3 5 GPT OSS 20B A4B Preview HF is an open-source language model by OpenGVLab. Features: 20b LLM, VRAM: 42.2GB, License: apache-2.0, LLM Explorer Score: 0.25.

  Arxiv:2312.14238   Arxiv:2404.16821   Arxiv:2411.10442   Arxiv:2412.05271   Arxiv:2504.10479   Arxiv:2508.18265 Base model:merge:openai/gpt-os... Base model:merge:opengvlab/int...   Base model:openai/gpt-oss-20b Base model:opengvlab/internvit...   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-GPT-OSS-20B-A4B-Preview-HF 

InternVL3 5 GPT OSS 20B A4B Preview HF Parameters and Internals

LLM NameInternVL3 5 GPT OSS 20B A4B Preview HF
Repository 🤗https://huggingface.co/OpenGVLab/InternVL3_5-GPT-OSS-20B-A4B-Preview-HF 
Base Model(s)  OpenGVLab/InternViT-300M-448px-V2_5   GPT Oss 20B   OpenGVLab/InternViT-300M-448px-V2_5   openai/gpt-oss-20b
Model Size20b
Required VRAM42.2 GB
Updated2026-08-08
MaintainerOpenGVLab
Model Typeinternvl
Model Files  4.6 GB: 1-of-9   4.9 GB: 2-of-9   4.9 GB: 3-of-9   4.9 GB: 4-of-9   4.9 GB: 5-of-9   4.9 GB: 6-of-9   4.9 GB: 7-of-9   4.9 GB: 8-of-9   3.3 GB: 9-of-9
Model ArchitectureInternVLForConditionalGeneration
Licenseapache-2.0
Model Max Length131072
Transformers Version4.55.0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|endoftext|>
Torch Data Typebfloat16