Is gemma-4-E4B-it-qat-q4_0-unquantized or Qwen3.6-35B-A3B smaller?

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

Which uses less memory at long context?

gemma-4-E4B-it-qat-q4_0-unquantized — its KV cache at 32K context is 1.2x smaller, because of how its attention layers cache.

Model comparison

gemma-4-E4B-it-qat-q4_0-unquantized vs Qwen3.6-35B-A3B

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: gemma-4-E4B-it-qat-q4_0-unquantized's KV cache at 32K is 1.2× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	gemma-4-E4B-it-qat-q4_0-unquantized	Qwen3.6-35B-A3B
Parameters	7.9B	36.0B
Architecture	gemma4	qwen35moe
Layers	42	40
Native context	131,072	262,144
Mixture of experts	no	yes, 256 experts
Quantizations published	1	61
Smallest quantization	4.80 GiB	8.77 GiB
Q4_K_M	—	19.71 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	gemma-4-E4B-it-qat-q4_0-unquantized	Qwen3.6-35B-A3B	Ratio
4,096	0.12 GiB	0.08 GiB	1.57×
8,192	0.18 GiB	0.16 GiB	1.14×
16,384	0.29 GiB	0.31 GiB	1.09×
32,768	0.51 GiB	0.63 GiB	1.24×
65,536	0.94 GiB	1.25 GiB	1.33×
131,072	1.82 GiB	2.50 GiB	1.37×