Is gemma-4-31B-it-qat-q4_0-unquantized-assistant 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 3.9x smaller, because of how its attention layers cache.

Model comparison

gemma-4-31B-it-qat-q4_0-unquantized-assistant 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 3.9× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	gemma-4-31B-it-qat-q4_0-unquantized-assistant	embeddinggemma-300m
Parameters	470M	303M
Architecture	gemma4-assistant	gemma-embedding
Layers	4	24
Native context	262,144	2,048
Mixture of experts	no	no
Quantizations published	13	10
Smallest quantization	0.29 GiB	0.26 GiB
Q4_K_M	0.33 GiB	—
Licence	apache-2.0	—

KV cache by context

the term that decides long-context viability

Context	gemma-4-31B-it-qat-q4_0-unquantized-assistant	embeddinggemma-300m	Ratio
4,096	0.13 GiB	0.04 GiB	3.78×
8,192	0.20 GiB	0.05 GiB	3.85×
16,384	0.32 GiB	0.08 GiB	3.90×
32,768	0.57 GiB	0.14 GiB	3.95×
65,536	1.07 GiB	0.27 GiB	3.97×
131,072	2.07 GiB	0.52 GiB	3.98×