Is Qwen3.5-4B-DFlash 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 1.5x smaller, because of how its attention layers cache.

Model comparison

Qwen3.5-4B-DFlash 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 1.5× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.5-4B-DFlash	embeddinggemma-300m
Parameters	634M	303M
Architecture	dflash	gemma-embedding
Layers	6	24
Native context	262,144	2,048
Mixture of experts	no	no
Quantizations published	8	10
Smallest quantization	0.23 GiB	0.26 GiB
Q4_K_M	0.36 GiB	—
Licence	apache-2.0	—

KV cache by context

the term that decides long-context viability

Context	Qwen3.5-4B-DFlash	embeddinggemma-300m	Ratio
4,096	0.09 GiB	0.04 GiB	2.67×
8,192	0.12 GiB	0.05 GiB	2.35×
16,384	0.15 GiB	0.08 GiB	1.83×
32,768	0.21 GiB	0.14 GiB	1.47×
65,536	0.34 GiB	0.27 GiB	1.25×
131,072	0.59 GiB	0.52 GiB	1.13×