Qwen3-Reranker-4B is not named as a product on any indexed page, so no source confirms a direct listing for that exact 4B model. The closest matches are Replicate's hosted Qwen3 Reranker 8B action 111, which reranks search results with a Qwen3 reranker, and the Sentence Transformers library, which is the standard Python module for running reranker models locally 10. Your choice depends on whether you want a hosted API or a local model; if you run it yourself, Sentence Transformers covers l
A question back: Do you want to run Qwen3-Reranker-4B through a hosted API or on your own machine, and which platform or hardware will you use?
- 1
Replicatereplicate.comverified and signed
Replicate hosts open-source models behind a cloud API, including tejasunku/qwen3-reranker-8b, which reranks query search results with the Qwen3 reranker 8B model and supports instructions 11; this is the 8B variant, not the 4B model.
for agents: tejasunku/qwen3-reranker-8b
- 2
Sentence Transformerssbert.netverified and signed
Sentence Transformers is the Python module for using and training embedding and reranker models, so it can load and run a Qwen3 reranker locally 10; its page does not list Qwen3-Reranker-4B by name.
official:SDK · sentence-transformers+24 community tools built for it
for agents: XLNet · BERT · deep
- 3
Jina AIjina.aifound in code, not yet checked
Jina offers rerankers with a sort_by_relevance action that reranks a list of documents against a query using the Jina Reranker API 17; it is a different model family, not Qwen3.
for agents: sort_by_relevance · sort_by_relevance · expand_query
- 4
ZeroEntropyzeroentropy.devfound in code, not yet checked
ZeroEntropy trains and offers specialized rerankers and embeddings for production search and RAG pipelines 6; its search action queries documents through the ZeroEntropy service 16.
+1 community tools built for it
for agents: probe_search · search · probe_index
Sources
- 1Replicate - Run AI with an APIreplicate.com · read 2026-10-29
- 6ZeroEntropy — Specialized AI Models for Every Systemzeroentropy.dev · read 2026-10-30
- 7Jina AI - Your Search Foundation, Supercharged.jina.ai · read 2026-10-29
- 10SentenceTransformers Documentation — Sentence Transformers documentationsbert.net · read 2026-10-29
- 11tejasunku/qwen3-reranker-8b: declares "tejasunku/qwen3-reranker-8b" (the record we read and signed)unfragile.ai · read 2026-10-24
- 16probe: declares "probe_search" (the record we read)github.com · read 2026-10-24
- 17Jina AI Remote MCP Server: declares "sort_by_relevance" (the record we read)github.com · read 2026-10-24
For agents: the 10 actions behind this answer
tejasunku/qwen3-reranker-8b · tejasunku/qwen3-reranker-8b verified and signed
Rerank query search results using qwen3 reranker 8b model, with support for instructions
lucataco/qwen3-embedding-8b · lucataco/qwen3-embedding-8b verified and signed
The Qwen3 Embedding model series is specifically designed for text embedding and ranking tasks
prunaai/qwen3-32b · prunaai/qwen3-32b verified and signed
A 2x faster qwen 3 model through pruna oss
qwen/qwen3-235b-a22b-instruct-2507 · qwen/qwen3-235b-a22b-instruct-2507 verified and signed
Updated Qwen3 model for instruction following
ditto--ai/qwen3guard-gen-4b · ditto--ai/qwen3guard-gen-4b verified and signed
A 4B-parameter safety and content moderation model that classifies user prompts and assistant responses as Safe, Unsafe, or Controversial with fine-grained category labels and refusal detection. Supports 119 languages.
lucataco/qwen3-vl-8b-instruct · lucataco/qwen3-vl-8b-instruct verified and signed
A powerful vision-language model in the Qwen series
ninehills/bge-reranker-base · ninehills/bge-reranker-base verified and signed
BAAI/bge-reranker-base Model with fp16
qwen/qwen3-7-plus · qwen/qwen3-7-plus verified and signed
Qwen3.7-Plus is Alibaba's cost-effective multimodal model with vision-language understanding, a 1 million token context window, and strong agentic coding and tool use.
yxzwayne/bge-reranker-v2-m3 · yxzwayne/bge-reranker-v2-m3 verified and signed
Newest balance-striking reranker model from BAAI. Outputs rank scores for query-doc pairs. FP16 inference enabled.
sesamo-srl/bge-reranker-v2-m3 · sesamo-srl/bge-reranker-v2-m3 verified and signed
Newest reranker model from BAAI (https://huggingface.co/BAAI/bge-reranker-v2-m3). FP16 inference enabled. Normalize param available
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.