LM Studio

ModelsDocsBlogEnterpriseLM LinkNew

Download

Models

Developer Docs

LM Link

New

Careers

We're Hiring

Blog

Changelog

Enterprise Solutions

titi14

Stats

1 Download

Capabilities

Vision Input

Trained for tool use

Minimum system memory

3GB

Tags

qwen3_vl

Last updated

Updated on November 28by

titi14

Report

Product

Download the app Models LM LinkNew LM Studio Hub Beta Releases Changelog

Developer

Developer Docs lmstudio-js lmstudio-python LM Studio CLI (lms)llms.txt llms-full.txt

Company

Legal

LinkedIn GitHub Discord Twitter / X

Product

Download the app Models LM LinkNew LM Studio Hub Beta Releases Changelog

Developer

Developer Docs lmstudio-js lmstudio-python LM Studio CLI (lms)llms.txt llms-full.txt

Company

Legal

titi14/qwen3-vl-2b • LM Studio Hub

titi14

Stats

1 Download

Capabilities

Vision Input

Trained for tool use

Minimum system memory

3GB

Qwen3 VL 2B

The latest generation vision-language model in the Qwen series with comprehensive upgrades to visual perception and spatial reasoning.

Key Features

Parameters

Custom configuration options included with this model

Repeat Penalty

Disabled

Temperature

0.7

Top K Sampling

Top P Sampling

0.8

Sources

The underlying model files this model uses

qwen3-vl-2b

Public

Forked from qwen/qwen3-vl-2b

Model

Revisions

Visual Agent: Operates PC and mobile GUIs—recognizes elements, understands functions, and completes tasks

Visual Coding: Generates Draw.io, HTML, CSS, and JavaScript from images and videos

Advanced Spatial Perception: Provides 2D/3D grounding for spatial reasoning and embodied AI applications

Upgraded Recognition: Recognizes celebrities, anime, products, landmarks, flora, fauna, and more

Expanded OCR: Supports 32 languages with robust performance in low light, blur, and tilt conditions

Pure Text Performance: Text understanding on par with pure LLMs through seamless text-vision fusion

Architecture Highlights

2B parameters
DeepStack for fine-grained detail capture
Text-Timestamp Alignment for precise event localization
Context length: 256,000 tokens
Vision-enabled multimodal model

Performance

Delivers strong vision-language performance across diverse tasks including document analysis, visual question answering, and agentic interactions.

Based on

🤗lmstudio-community/Qwen3-VL-2B-Instruct-MLX-8bit→

MLX

🤗lmstudio-community/Qwen3-VL-2B-Instruct-GGUF→

GGUF