Model comparison

nomic-embed-text-v1 vs jina-reranker-v1-tiny-en

At Q4_K_M, jina-reranker-v1-tiny-en is the smaller download — 33,257,536 bytes against 84,106,624. At long context the gap widens: jina-reranker-v1-tiny-en's KV cache at 32K is 6.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

nomic-embed-text-v1jina-reranker-v1-tiny-en
Parameters137M33M
Architecturenomic-bertjina-bert-v2
Layers124
Native context8,1928,192
Mixture of expertsnono
Quantizations published1412
Smallest quantization0.05 GiB0.03 GiB
Q4_K_M0.08 GiB0.03 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
Contextnomic-embed-text-v1jina-reranker-v1-tiny-enRatio
4,0960.14 GiB0.02 GiB6.00×
8,1920.28 GiB0.05 GiB6.00×
16,3840.56 GiB0.09 GiB6.00×
32,7681.13 GiB0.19 GiB6.00×
65,5362.25 GiB0.38 GiB6.00×
131,0724.50 GiB0.75 GiB6.00×