LLM EXPLORER 61,652 MODELS INDEXED

SFT 4B ScaleCUA EvoCUA by HaoranLiu

By HaoranLiu · 28 downloads
HF Repo ↗ Copy URL

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: 0.28.

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 NameSFT 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 Size4b
Required VRAM8.9 GB
Updated2026-09-19
MaintainerHaoranLiu
Model Typeqwen3_vl
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   3.9 GB: 2-of-2
Model ArchitectureQwen3VLForConditionalGeneration
Licenseother
Model Max Length262144
Transformers Version5.6.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to SFT 4B ScaleCUA EvoCUA

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 VL 4B Instruct0K / 8.9 GB3611570437
MinerU Popo0K / 17.6 GB268954
Qwen3 VL 4B Instruct FP80K / 6.1 GB30110365
Spatial Interactor Qwen3 VL 4B0K / 9.7 GB820
VecLang 4B0K / 8.9 GB631
...l 4B Uvd Racer Hl6k Cs16 Final0K / 9.7 GB181
...rallelTubeDecoding Qwen3 VL 4B0K / 8.9 GB772
SpatialBlock 4B Direct0K / 8.9 GB440
SpatialBlock 4B Reason0K / 9.7 GB290
Qwen3 VL 4B Instruct0K / 8.9 GB1786411
Note: green Score (e.g. "73.2") means that the model is better than HaoranLiu/SFT-4B-ScaleCUA-EvoCUA.