Is Huihui-gemma-3n-E4B-it-abliterated or gemma-4-E4B-it smaller?

Huihui-gemma-3n-E4B-it-abliterated is smaller at Q4_K_M: 3.95 GiB against 4.64 GiB.

Which uses less memory at long context?

Huihui-gemma-3n-E4B-it-abliterated — its KV cache at 32K context is 1.0x smaller, because of how its attention layers cache.

Model comparison

At Q4_K_M, Huihui-gemma-3n-E4B-it-abliterated is the smaller download — 4,237,064,192 bytes against 4,977,171,584.

From the file· summed bytes, KV per layer

	Huihui-gemma-3n-E4B-it-abliterated	gemma-4-E4B-it
Parameters	7.8B	8.0B
Architecture	gemma3n	gemma4
Layers	35	42
Native context	32,768	131,072
Mixture of experts	no	no
Quantizations published	33	36
Smallest quantization	2.57 GiB	3.30 GiB
Q4_K_M	3.95 GiB	4.64 GiB
Licence	gemma	apache-2.0

the term that decides long-context viability

Context	Huihui-gemma-3n-E4B-it-abliterated	gemma-4-E4B-it	Ratio
4,096	0.11 GiB	0.12 GiB	1.13×
8,192	0.16 GiB	0.18 GiB	1.08×
16,384	0.27 GiB	0.29 GiB	1.05×
32,768	0.49 GiB	0.51 GiB	1.03×
65,536	0.93 GiB	0.94 GiB	1.01×
131,072	1.80 GiB	1.82 GiB	1.01×