Model catalogue · Alibaba Cloud (Qwen)

Qwen Rerank

The reranking tier of the Qwen family selects the genuinely pertinent passages from the candidates of a file search before the language model gets to see them, and stays small enough to run alongside language model and embedding on the same graphics card. Under professional-secrecy law the route decides: in dedicated operation on reserved hardware in a German data centre the chain is closed - open weights, no model vendor anything is transmitted to, and the data centre operator bound via the chain obligation under section 203(4) of the German Criminal Code. Via IONOS, by contrast, the product-specific confirmation of the section 203 clause is still outstanding, even though the reranking has file extracts before it in plain text.

Available through us

Everything section 203 requires is settled, including the provider's confidentiality undertaking, and nothing is stored at the provider, apart from a technical cache of a few minutes for Claude (zero retention). You do not have to clarify anything further.

What it is good for

  • Lifts the hit quality of a file search clearly above pure embedding search
  • 0.6 billion parameters in BF16, around 4 GB - fits alongside generator and embedding on one card
  • Apache 2.0, available from German data centres or on the dedicated instance

Where it stops

  • A side role in the search pipeline - without embedding and a language model it has no function
  • It is given file extracts in plain text; contractually it has to be treated like a language model
  • The product-specific confirmation of the section 203 clause for the AI Model Hub is still outstanding

Status through us

The same model, procured differently, is a different legal position. The status above refers to procurement through us; processing takes place in Germany.

Which route carries it, with which instrument and under which condition, we set out in full to the firm before it commissions us - section 203(4) requires that the chain can be checked, not that it is published. The full matrix, with the sources behind every route, can be requested in the German catalogue after confirming your e-mail address, and we go through it in the conversation.

Is Qwen Rerank the right fit?

We go through your tasks and the route that carries them - and say plainly where it does not.

Arrange a conversation