Is gemma-4-E4B-it-ultra-uncensored-heretic or Qwen3.6-35B-A3B smaller?

gemma-4-E4B-it-ultra-uncensored-heretic is smaller at Q4_K_M: 4.97 GiB against 19.71 GiB.

Which uses less memory at long context?

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

Model comparison

gemma-4-E4B-it-ultra-uncensored-heretic vs Qwen3.6-35B-A3B

At Q4_K_M, gemma-4-E4B-it-ultra-uncensored-heretic is the smaller download — 5,335,286,336 bytes against 21,166,757,728. At long context the gap widens: gemma-4-E4B-it-ultra-uncensored-heretic'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-ultra-uncensored-heretic	Qwen3.6-35B-A3B
Parameters	8.0B	36.0B
Architecture	gemma4	qwen35moe
Layers	42	40
Native context	131,072	262,144
Mixture of experts	no	yes, 256 experts
Quantizations published	24	61
Smallest quantization	4.10 GiB	8.77 GiB
Q4_K_M	4.97 GiB	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-ultra-uncensored-heretic	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×