🚀 Qwen3-Embedding-0.6B CPU API (under 2s)

Best CPU-friendly model from the Qwen3 family. 0.6B params • 1024-dim • 32k context • 100+ languages • <2s latency on free CPU. Powered by Qwen/Qwen3-Embedding-0.6B on Hugging Face Spaces.

Input Texts (one per line)

Use Query Mode (recommended for search/retrieval)

Adds task-specific instruction – huge boost for RAG

Embedding Response

Examples