What are the hardware requirements for ShowUI 2B?

ShowUI 2B requires approximately 4.4 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed ShowUI 2B and how large is it?

ShowUI 2B is developed by showlab, a model with 2b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate ShowUI 2B?

ShowUI 2B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

ShowUI 2B by showlab — VRAM 4.4GB, 32K context

Name: ShowUI 2B
Author: showlab

ShowUI 2B is an open-source language model by showlab. Features: 2b LLM, VRAM: 4.4GB, Context: 32K, License: mit, Instruction-Based.

Arxiv:2411.17465 Base model:finetune:qwen/qwen2... Base model:qwen/qwen2-vl-2b-in... Computer use Eval-results Gui agents Instruct Pytorch Qwen2 vl Region:us Vision Vision-language-action model

Model Card on HF 🤗: https://huggingface.co/showlab/ShowUI-2B

ShowUI 2B Parameters and Internals

LLM Name	ShowUI 2B
Repository 🤗	https://huggingface.co/showlab/ShowUI-2B
Base Model(s)	Qwen2 VL 2B Instruct Qwen/Qwen2-VL-2B-Instruct
Model Size	2b
Required VRAM	4.4 GB
Updated	2026-08-08
Maintainer	showlab
Model Type	qwen2_vl
Instruction-Based	Yes
Model Files	4.4 GB
Model Architecture	Qwen2VLForConditionalGeneration
License	mit
Context Length	32768
Model Max Length	32768
Transformers Version	4.45.0.dev0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the ShowUI 2B capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Quantized Models of the ShowUI 2B

Model	Likes	Downloads	VRAM
ShowUI 2B 6bit V2	1	22	2 GB

Best Alternatives to ShowUI 2B

Best Alternatives	Context / RAM	Downloads	Likes
Qwen2 VL 2B Instruct	32K / 4.4 GB	3	24
Qwen2 VL 2B Instruct Bf16	32K / 4.4 GB	90	1
Qwen2 VL 2B Instruct 4bit	32K / 1.2 GB	3899	7
Qwen2 VL 2B Instruct 8bit	32K / 2.4 GB	99	2
Qwen2 VL 2B Instruct AWQ	32K / 3 GB	3752	26
Qwen2 VL 2B Instruct GPTQ Int4	32K / 2.5 GB	793	28
Qwen2 VL 2B Instruct GPTQ Int8	32K / 3.1 GB	471	17

Note: green Score (e.g. "73.2") means that the model is better than showlab/ShowUI-2B.