ahmadwaqar/ mai-ui

187 1 month ago

Alibaba Tongyi GUI agent on Qwen3-VL. SOTA: 73.5% ScreenSpot-Pro, 76.7% AndroidWorld. Returns bbox [x1,y1,x2,y2] for UI automation. Supports MCP tools & device-cloud collaboration. Apache 2.0. Tags: 2b (default), 8b.

vision 2b 8b

3 models

mai-ui:latest
cf0ee985da1d • 4.3GB • 256K context window •
Text, Image input • 1 month ago
mai-ui:2b latest
cf0ee985da1d • 4.3GB • 256K context window •
Text, Image input • 1 month ago
mai-ui:8b
82b0817821c1 • 18GB • 256K context window •
Text, Image input • 1 month ago