Kimi-VL-A3B-Instruct is a 3-billion-parameter multimodal model developed by Moonshot AI. It processes both image and text inputs and generates coherent responses following user instructions. The model uses a specialized chat template and is designed for vision-language tasks including visual question answering and image captioning.
Kimi VL A3B Instruct is a Foundation models & chat product. It focuses on understanding and reasoning over both images and text in a conversational setting. Kimi VL A3B Instruct is an open-source project aimed at developers building multimodal AI applications. The project is open source (MIT). The product ships for the web, the command line, and API.
Behind Kimi VL A3B Instruct is Moonshot AI, and the product first shipped in 2025. The project is developed in the open on GitHub with 1.2k stars. Among its 3 catalogued features are Vision-Language Understanding, Instruction Following, and Multimodal Chat. It exposes integrations via a public API.
Latest indexed changes and source events
moonshotai/Kimi-VL-A3B-Instruct verified by the PulseGate indexer
Other apps tracked under the same category.
