Who should use this model?
- Improving top results after embedding search in serious document search apps with enough compute and patience.
Choose something else when
- You only need basic local search, or your app cannot call reranking models afterwards reliably.
What hardware makes sense?
The download is only part of the memory needed. Leave room for the app, the input it processes, and other open programs. Document-search memory also depends on input length, batch size, and the document index; a chat-memory estimate does not confirm that workload.
- CPU only
- Use a smaller model for this memory limit.
- 8GB system memory
- Check this model with your exact hardware and settings before choosing it.
- 16GB system memory
- Check this model with your exact hardware and settings before choosing it.
- 32GB system memory
- Check this model with your exact hardware and settings before choosing it.
- 8GB GPU memory
- Check this model with your exact hardware and settings before choosing it.
- 12GB GPU memory
- Check this model with your exact hardware and settings before choosing it.
- 24GB GPU memory
- Check this model with your exact hardware and settings before choosing it.
- Apple unified memory
- Check this model with your exact hardware and settings before choosing it.
Model facts that change the decision
- Parameters
- 0.6B
- Input
- Text
- Published context limit
- 32,768 tokens
- Model format
- safetensors · sentence-transformers
- Languages
- 100+ languages, including programming languages
Ranking document-search results
A reranker scores passages found by an earlier search. Choose an app that supports this exact reranker; keep a separate embedding model for the search index and a separate chat model for answers.
Check the setup instructions
A ready-to-follow setup for a local chat app is not supplied here. Follow the official model card for this exact model and task.
Conditions that change the answer
- This model sorts document-search results by relevance; it does not chat or build an embedding index.
- Use the model’s own setup instructions; an Ollama command is not available here.
- TEI compatibility is not recommended unless Hugging Face adds Qwen3 Reranker support to its reranking model list.
- Check the required memory and supported model formats in the setup instructions before downloading.
- Commercial use: Yes under Apache-2.0.
- Qwen3 Reranker 0.6B is not an embedder; it reviews candidate passages after search and scores relevance. It can improve answer quality in document search, but adds latency, setup complexity, and another model to manage in production.
Read the controlling license text →