01

Basic information

Model repository: moonshotai/Kimi-VL-A3B-Instruct
Organization: moonshotai
Tasks: image-text-to-text

02

Architecture and runtime

Model type: kimi_vl
Architecture: KimiVLForConditionalGeneration
Libraries: transformer, safetensors, pytorch
Base models: moonshotai/Moonlight-16B-A3B
Current revision: master

03

License and update history

License: mit
Created: 2025-11-27
Last updated: 2026-01-31

agentvideoscreenspotlong-context
04

Hardware requirements

Not filled in locally.

05

Download links

Not filled in locally.

06

Basic usage example

Not filled in locally.