LLM EXPLORER 56,604 MODELS INDEXED

ScaleCUA 32B by OpenGVLab

By OpenGVLab · 66 downloads
HF Repo ↗ Copy URL

ScaleCUA 32B is an open-source language model by OpenGVLab. Features: 32b LLM, VRAM: 67.2GB, 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-32b...   Conversational Dataset:opengvlab/scalecua-dat...   Deploy:azure   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-32B 

ScaleCUA 32B Parameters and Internals

LLM NameScaleCUA 32B
Repository 🤗https://huggingface.co/OpenGVLab/ScaleCUA-32B 
Base Model(s)  Qwen/Qwen2.5-VL-32B-Instruct   Qwen/Qwen2.5-VL-32B-Instruct
Model Size32b
Required VRAM67.2 GB
Updated2026-08-08
MaintainerOpenGVLab
Model Typeqwen2_5_vl
Instruction-BasedYes
Model Files  5.0 GB: 1-of-14   4.9 GB: 2-of-14   4.9 GB: 3-of-14   4.9 GB: 4-of-14   4.9 GB: 5-of-14   4.9 GB: 6-of-14   4.9 GB: 7-of-14   4.9 GB: 8-of-14   4.9 GB: 9-of-14   4.9 GB: 10-of-14   4.9 GB: 11-of-14   4.9 GB: 12-of-14   4.9 GB: 13-of-14   3.4 GB: 14-of-14
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 32B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 VL 32B Instruct Bf16125K / 67.3 GB3045
Qwen2.5 VL 32B Instruct 4bit125K / 19.8 GB4414
Qwen2.5 VL 32B Instruct 8bit125K / 36.2 GB1834
Qwen2.5 VL 32B Instruct 6bit125K / 28 GB771