Is gemma-4-E2B-it-qat-q4_0-unquantized or Qwen3-30B-A3B-Thinking-2507 smaller?

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

Which uses less memory at long context?

gemma-4-E2B-it-qat-q4_0-unquantized — its KV cache at 32K context is 12.2x smaller, because of how its attention layers cache.

Model comparison

gemma-4-E2B-it-qat-q4_0-unquantized vs Qwen3-30B-A3B-Thinking-2507

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: gemma-4-E2B-it-qat-q4_0-unquantized's KV cache at 32K is 12.2× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	gemma-4-E2B-it-qat-q4_0-unquantized	Qwen3-30B-A3B-Thinking-2507
Parameters	5.1B	30.5B
Architecture	gemma4	qwen3moe
Layers	35	48
Native context	131,072	262,144
Mixture of experts	no	yes, 128 experts
Quantizations published	3	51
Smallest quantization	3.12 GiB	7.05 GiB
Q4_K_M	—	17.28 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	gemma-4-E2B-it-qat-q4_0-unquantized	Qwen3-30B-A3B-Thinking-2507	Ratio
4,096	0.05 GiB	0.38 GiB	6.86×
8,192	0.08 GiB	0.75 GiB	9.14×
16,384	0.14 GiB	1.50 GiB	10.97×
32,768	0.25 GiB	3.00 GiB	12.19×
65,536	0.46 GiB	6.00 GiB	12.91×
131,072	0.90 GiB	12.00 GiB	13.30×