LocalOps
Back to Calculator

Qwen3 Embedding 0.6B

Ultra-compact Qwen3 embedding model — 0.6B parameters, runs on CPU or any GPU. Ideal for edge RAG pipelines and low-latency local search with Apache 2.0 license.

Model Specifications

ArchitectureEMBEDDING
Parameters0.6B
Familyqwen3-embed
VRAM (Q4)0.3GB
Works as a dense retrieval backbone for reranking pipelines. Can be combined with Qwen3-Reranker-0.6B for full RAG stack.
#alibaba#qwen#embedding#retrieval#rag#edge#apache2#efficientSource

Share this Model

Send this model's specs directly to your community.

Post