qwen3-embedding-0-6b
The default small pick: multilingual + instruction-aware + long context at 0.6B; pairs with Qwen3-Reranker.
Run Qwen3-Embedding-0.6B as a live endpoint on one of your nodes.
Target
Couldn't load your nodes
missing authorization header (HTTP 401)
Runs on your node’s hardware · billed per running minute to your org. Health-gated — it goes live only once the endpoint answers. Stop it anytime from Deployments.
