Embedding
300M
Open weights
Kawn Embed Light
Lightweight general-purpose Arabic embeddings for semantic search, retrieval, clustering, and RAG.
Lightweight general-purpose Arabic text embedding model (300M parameters). Built for ultra-fast, production-grade semantic search, RAG pipelines, and classification. Tuned for standard business and general Arabic content. State-of-the-art performance among Arabic embedding models under one billion parameters.
Access
Cloud API
On-premises
Let's talk about what you're trying to build.
Tell us the problem. We'll tell you honestly whether AI is the right answer.