Qwen3-Reranker-4B-Q4_K_M-GGUF

Qwen3 Reranker 4B Q4_K_M GGUF

This repository contains the exact immutable local-model asset used by NovelAide. This GGUF is a NovelAide-built derived artifact produced from the official Safetensors checkpoint. It is not an official Qwen GGUF release.

Provenance

• Base model: Qwen/Qwen3-Reranker-4B
• Asset source: Qwen/Qwen3-Reranker-4B
• Pinned source revision: 22e683669bc0f0bd69640a1354a6d0aebcfeede5
• Runtime: llama-cpp
• NovelAide asset ID: qwen3-reranker-4b
• NovelAide CDN prefix: qwen3-reranker-4b-gguf/d918c211d3ba339b

The base model and conversion input are the official Qwen/Qwen3-Reranker-4B Safetensors at immutable revision 22e683669bc0f0bd69640a1354a6d0aebcfeede5.

NovelAide converts that checkpoint to BF16 GGUF and then quantizes it to Q4_K_M with ggml-org/llama.cpp tag b9842, commit 6f4f53f2b7da54fcdbbecaaa734337c337ad6176. This is the llama.cpp revision embedded by the Desktop runtime's [email protected].

The resulting GGUF is a NovelAide-built derived asset, not an upstream Qwen GGUF. Its immutable content-addressed object prefix is qwen3-reranker-4b-gguf/d918c211d3ba339b; it must not overwrite the previously published community-derived artifact.

Files

Usage

Use the GGUF files with a compatible llama.cpp runtime and the ONNX files with a compatible ONNX / Transformers.js runtime. NovelAide pins the exact files and checksums shown above; do not substitute similarly named quantizations.

License and attribution

The model asset follows the upstream apache-2.0 license. Review the linked base model and asset source model cards for their complete terms, limitations, and attribution requirements. NovelAide is not affiliated with or endorsed by the upstream model authors.