Model comparison

nomic-embed-text-v2-moe vs embeddinggemma-300m-qat-q8_0-unquantized

These two publish different quantization sets; the table below has the exact sizes.

From the file· summed bytes, KV per layer

Side by side

nomic-embed-text-v2-moeembeddinggemma-300m-qat-q8_0-unquantized
Parameters475M303M
Architecturenomic-bert-moegemma-embedding
Layers1224
Native context2,048
Mixture of expertsyes, 8 expertsno
Quantizations published201
Smallest quantization0.25 GiB0.31 GiB
Q4_K_M0.32 GiB
Licenceapache-2.0gemma

KV cache by context

the term that decides long-context viability
Contextnomic-embed-text-v2-moeembeddinggemma-300m-qat-q8_0-unquantizedRatio
4,0960.04 GiB
8,1920.05 GiB
16,3840.08 GiB
32,7680.14 GiB
65,5360.27 GiB
131,0720.52 GiB