zerank-1-GGUF

zerank-1 is a state-of-the-art reranker developed by ZeroEntropy to significantly enhance retrieval accuracy in search engines. Unlike most SOTA rerankers that are closed-source and proprietary, zerank-1 outperforms top models like Cohere-Rerank-v3.5 and Salesforce/LlamaRank-v1 across diverse domains including finance, legal, code, STEM, medical, and conversational data.

Model files

File	Size	Format
zerank-1.BF16.gguf	8.05 GB	BF16
zerank-1.F16.gguf	8.05 GB	F16
zerank-1.F32.gguf	16.1 GB	F32
zerank-1.Q2_K.gguf	1.67 GB	Q2_K
zerank-1.Q3_K_L.gguf	2.24 GB	Q3_K_L
zerank-1.Q3_K_M.gguf	2.08 GB	Q3_K_M
zerank-1.Q3_K_S.gguf	1.89 GB	Q3_K_S
zerank-1.Q4_K_M.gguf	2.5 GB	Q4_K_M
zerank-1.Q4_K_S.gguf	2.38 GB	Q4_K_S
zerank-1.Q5_K_M.gguf	2.89 GB	Q5_K_M
zerank-1.Q5_K_S.gguf	2.82 GB	Q5_K_S
zerank-1.Q6_K.gguf	3.31 GB	Q6_K
zerank-1.Q8_0.gguf	4.28 GB	Q8_0
.gitattributes	2.39 kB	-
README.md	462 Bytes	-
config.json	29 Bytes	-

Quants Usage

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):