Model comparison

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

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

From the file· summed bytes, KV per layer

Side by side

embeddinggemma-300m-qat-q8_0-unquantizednomic-embed-text-v2-moe
Parameters303M475M
Architecturegemma-embeddingnomic-bert-moe
Layers2412
Native context2,048
Mixture of expertsnoyes, 8 experts
Quantizations published120
Smallest quantization0.31 GiB0.25 GiB
Q4_K_M0.32 GiB
Licencegemmaapache-2.0

KV cache by context

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