What are the hardware requirements for SFT 4B ScaleCUA EvoCUA?

SFT 4B ScaleCUA EvoCUA requires approximately 8.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed SFT 4B ScaleCUA EvoCUA and how large is it?

SFT 4B ScaleCUA EvoCUA is developed by HaoranLiu, a model with 4b 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 SFT 4B ScaleCUA EvoCUA?

SFT 4B ScaleCUA EvoCUA is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

SFT 4B ScaleCUA EvoCUA by HaoranLiu — VRAM 8.9GB

Name: SFT 4B ScaleCUA EvoCUA
Author: HaoranLiu

SFT 4B ScaleCUA EvoCUA is an open-source language model by HaoranLiu. Features: 4b LLM, VRAM: 8.9GB, License: other, Instruction-Based, LLM Explorer Score: 0.25.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-vl-4b-in... Computer-use Conversational Endpoints compatible Gui-agent Image-text-to-text Instruct Osworld Qwen3 vl Region:us Safetensors Scalecua Sft Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/HaoranLiu/SFT-4B-ScaleCUA-EvoCUA

SFT 4B ScaleCUA EvoCUA Parameters and Internals

LLM Name	SFT 4B ScaleCUA EvoCUA
Repository 🤗	https://huggingface.co/HaoranLiu/SFT-4B-ScaleCUA-EvoCUA
Base Model(s)	Qwen3 VL 4B Instruct Qwen/Qwen3-VL-4B-Instruct
Model Size	4b
Required VRAM	8.9 GB
Updated	2026-09-19
Maintainer	HaoranLiu
Model Type	qwen3_vl
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-2 3.9 GB: 2-of-2
Model Architecture	Qwen3VLForConditionalGeneration
License	other
Model Max Length	262144
Transformers Version	5.6.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the SFT 4B ScaleCUA EvoCUA 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

Best Alternatives to SFT 4B ScaleCUA EvoCUA

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3 VL 4B Instruct	0K / 8.9 GB	3611570	437
FemboyAV 4B	0K / 8.9 GB	757	0
MinerU Popo	0K / 17.6 GB	26895	4
Qwen3 VL 4B Instruct FP8	0K / 6.1 GB	301103	65
UAV PUR 4B	0K / 8.9 GB	22	1
AA VL 4B	0K / 8.9 GB	87	0
Qwen3 VL 4B VQA SFT	0K / 8.9 GB	40	0
Kayak V2	0K / 17.7 GB	31	0
Op Hrg Qwen3vl4b Instruct	0K / 9.7 GB	51	2
Slayer Ocr Qwen3vl 4B Frozen	0K / 8.9 GB	39	0

Note: green Score (e.g. "73.2") means that the model is better than HaoranLiu/SFT-4B-ScaleCUA-EvoCUA.