Is Huihui-gemma-4-31B-it-abliterated-v2 or gemma-4-26B-A4B-it smaller?

gemma-4-26B-A4B-it is smaller at Q4_K_M: 15.64 GiB against 17.40 GiB.

Which uses less memory at long context?

gemma-4-26B-A4B-it — its KV cache at 32K context is 4.0x smaller, because of how its attention layers cache.

Model comparison

Huihui-gemma-4-31B-it-abliterated-v2 vs gemma-4-26B-A4B-it

At Q4_K_M, gemma-4-26B-A4B-it is the smaller download — 16,796,017,248 bytes against 18,687,058,336. At long context the gap widens: gemma-4-26B-A4B-it's KV cache at 32K is 4.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Huihui-gemma-4-31B-it-abliterated-v2	gemma-4-26B-A4B-it
Parameters	32.7B	26.5B
Architecture	gemma4	gemma4
Layers	60	30
Native context	262,144	262,144
Mixture of experts	no	yes, 128 experts
Quantizations published	35	46
Smallest quantization	6.66 GiB	8.99 GiB
Q4_K_M	17.40 GiB	15.64 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Huihui-gemma-4-31B-it-abliterated-v2	gemma-4-26B-A4B-it	Ratio
4,096	1.80 GiB	0.45 GiB	4.00×
8,192	2.42 GiB	0.61 GiB	4.00×
16,384	3.67 GiB	0.92 GiB	4.00×
32,768	6.17 GiB	1.54 GiB	4.00×
65,536	11.17 GiB	2.79 GiB	4.00×
131,072	21.17 GiB	5.29 GiB	4.00×