LLM EXPLORER 56,604 MODELS INDEXED

ScaleCUA 7B by OpenGVLab

By OpenGVLab · 115 downloads
HF Repo ↗ Copy URL

ScaleCUA 7B is an open-source language model by OpenGVLab. Features: 7b LLM, VRAM: 16.6GB, Context: 125K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.21.

  Agent Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-vl-7b-...   Conversational Dataset:opengvlab/scalecua-dat...   En   Endpoints compatible   Image-text-to-text   Instruct   Qwen2 5 vl   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/OpenGVLab/ScaleCUA-7B 

ScaleCUA 7B Parameters and Internals

LLM NameScaleCUA 7B
Repository 🤗https://huggingface.co/OpenGVLab/ScaleCUA-7B 
Base Model(s)  Qwen/Qwen2.5-VL-7B-Instruct   Qwen/Qwen2.5-VL-7B-Instruct
Model Size7b
Required VRAM16.6 GB
Updated2026-08-08
MaintainerOpenGVLab
Model Typeqwen2_5_vl
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.7 GB: 4-of-4
Supported Languagesen
Model ArchitectureQwen2_5_VLForConditionalGeneration
Licenseapache-2.0
Context Length128000
Model Max Length128000
Transformers Version4.51.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to ScaleCUA 7B

Best Alternatives
Context / RAM
Downloads
Likes
OmniLong Qwen2.5 VL 7B512K / 16.6 GB72
Qwen2.5 VL 7B Instruct FP4125K / 7.2 GB491653
Qwen2.5 VL 7B Instruct NVFP4125K / 7.2 GB809216
ZwZ 7B125K / 16.6 GB3210
Qwen2.5 VL 7B Instruct FP8125K / 10 GB10098
OlmOCR 2 7B 1025 Bf16125K / 16.6 GB1542
HuatuoGPT Vision 7B Qwen2.5VL125K / 16.6 GB35811
ViLaSR125K / 16.7 GB3818
Holo1 7B Bf16125K / 16.6 GB242
Qwen2.5 VL 7B Instruct Bf16125K / 16.6 GB1603
Note: green Score (e.g. "73.2") means that the model is better than OpenGVLab/ScaleCUA-7B.