Is granite-embedding-107m-multilingual or embeddinggemma-300m smaller?

Both publish quantizations; compare the table for the exact sizes.

Which uses less memory at long context?

embeddinggemma-300m — its KV cache at 32K context is 1.9x smaller, because of how its attention layers cache.

Model comparison

granite-embedding-107m-multilingual vs embeddinggemma-300m

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: embeddinggemma-300m's KV cache at 32K is 1.9× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	granite-embedding-107m-multilingual	embeddinggemma-300m
Parameters	107M	303M
Architecture	bert	gemma-embedding
Layers	6	24
Native context	514	2,048
Mixture of experts	no	no
Quantizations published	19	10
Smallest quantization	0.11 GiB	0.26 GiB
Q4_K_M	0.11 GiB	—
Licence	apache-2.0	—

KV cache by context

the term that decides long-context viability

Context	granite-embedding-107m-multilingual	embeddinggemma-300m	Ratio
4,096	0.04 GiB	0.04 GiB	1.00×
8,192	0.07 GiB	0.05 GiB	1.38×
16,384	0.14 GiB	0.08 GiB	1.71×
32,768	0.28 GiB	0.14 GiB	1.95×
65,536	0.56 GiB	0.27 GiB	2.09×
131,072	1.13 GiB	0.52 GiB	2.17×