Model comparison

embeddinggemma-300m-qat-q4_0-unquantized vs ced-base

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-q4_0-unquantizedced-base
Parameters303M86M
Architecturegemma-embeddingced
Layers24
Native context2,048
Mixture of expertsnono
Quantizations published23
Smallest quantization0.21 GiB0.12 GiB
Q4_K_M
Licencegemmaapache-2.0

KV cache by context

the term that decides long-context viability
Contextembeddinggemma-300m-qat-q4_0-unquantizedced-baseRatio
4,0960.04 GiB
8,1920.05 GiB
16,3840.08 GiB
32,7680.14 GiB
65,5360.27 GiB
131,0720.52 GiB