Is Huihui-gemma-4-E2B-it-qat-q4_0-unquantized-abliterated or gemma-4-E4B-it smaller?

Huihui-gemma-4-E2B-it-qat-q4_0-unquantized-abliterated is smaller at Q4_K_M: 3.18 GiB against 4.64 GiB.

Which uses less memory at long context?

Huihui-gemma-4-E2B-it-qat-q4_0-unquantized-abliterated — its KV cache at 32K context is 2.1x smaller, because of how its attention layers cache.

Model comparison

Huihui-gemma-4-E2B-it-qat-q4_0-unquantized-abliterated vs gemma-4-E4B-it

At Q4_K_M, Huihui-gemma-4-E2B-it-qat-q4_0-unquantized-abliterated is the smaller download — 3,416,119,296 bytes against 4,977,171,584. At long context the gap widens: Huihui-gemma-4-E2B-it-qat-q4_0-unquantized-abliterated's KV cache at 32K is 2.1× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Huihui-gemma-4-E2B-it-qat-q4_0-unquantized-abliterated	gemma-4-E4B-it
Parameters	5.1B	8.0B
Architecture	gemma4	gemma4
Layers	35	42
Native context	131,072	131,072
Mixture of experts	no	no
Quantizations published	28	36
Smallest quantization	2.16 GiB	3.30 GiB
Q4_K_M	3.18 GiB	4.64 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Huihui-gemma-4-E2B-it-qat-q4_0-unquantized-abliterated	gemma-4-E4B-it	Ratio
4,096	0.05 GiB	0.12 GiB	2.25×
8,192	0.08 GiB	0.18 GiB	2.17×
16,384	0.14 GiB	0.29 GiB	2.10×
32,768	0.25 GiB	0.51 GiB	2.06×
65,536	0.46 GiB	0.94 GiB	2.03×
131,072	0.90 GiB	1.82 GiB	2.02×