Kindly Note that this demo is running on Mac M1 8GB RAM with Qwen3VL-8B+llama-Server(Embedded in Apache Zeppelin AI Page)+Browser+DuckDB but still response speed is good(2x in gif).
Preview-01:AI-NLP+Apache Zeppelin Powered with Qwen3-VL-8B+llama-Server to Talk with databases in natural language and Faster Response.
TechnoFunctionalLearning 
You must be logged in to post a comment.