Zen Reranker 4B GGUF
4B Zen reranker, quantized to GGUF (Q4_K_M) for CPU and mixed CPU/GPU re-scoring with llama.cpp.
Repackaged from Qwen/Qwen3-Reranker-4B (apache-2.0, Alibaba Qwen), quantized to GGUF. Not trained from scratch — a permissively-licensed redistribution for the OSS-clean Zen model line.
Files
| File | Format |
|---|---|
zen-reranker-4B-Q4_K_M.gguf |
GGUF Q4_K_M |
Usage
Use with llama.cpp reranking support (llama-server --reranking, /v1/rerank). Full-precision safetensors: zenlm/zen-reranker-4B.
License
apache-2.0. Upstream: Qwen/Qwen3-Reranker-4B by Alibaba Qwen. This repository redistributes a quantized derivative under the same license.