Try Delta
← All models

Qwen3 VL

Alibaba · 2025 · Vision-language · dense & MoE

See, read, and act on what’s on screen. Qwen3 VL handles images, video, OCR in 32 languages, GUI agents, and spatial reasoning, so Delta can work with photos, PDFs, and UI captures without sending them anywhere.

Maker
Alibaba
Architecture
Vision-language · dense & MoE
Fits from
Phone / edge · 5 GB+ RAM
Context
up to 8K
Runs
Local Intelligence
VisionOCRAgentsMultilingualDocument OCRGUI agentsImage + text

Sizes

Qwen3 VL 2BQ4_K_M

requires 5 GB+ memory · 8K context · Phone / edge

1.8 GBWeights
Qwen3 VL 4BQ4_K_M

requires 6 GB+ memory · 8K context · Phone / edge

2.5 GBWeights
Qwen3 VL 8BQ4_K_M

requires 11 GB+ memory · 8K context · Laptop

5.5 GBWeights
Qwen3 VL 30B-A3BQ4_K_M

requires 32 GB+ memory · 8K context · Workstation

20 GBWeights

Memory at context length

Approximate working set for Qwen3 VL 2B as context grows.

4K
2.2 GB
8K
2.4 GB

Related families

Qwen3.5

A natively multimodal daily driver: text, vision, and compact reasoning on your machine.

Qwen3

Think when you need it, answer fast when you don’t: coding, math, and 119 languages, local.

Qwen3 Coder

A coding specialist for agentic engineering: function calling, tools, and repo-scale work locally.