Is supergemma4-26b-abliterated-multimodal or gemma-4-26B-A4B-it smaller?

supergemma4-26b-abliterated-multimodal is smaller at Q4_K_M: 15.64 GiB against 15.64 GiB.

Which uses less memory at long context?

gemma-4-26B-A4B-it — its KV cache at 32K context is 1.0x smaller, because of how its attention layers cache.

Model comparison

At Q4_K_M, supergemma4-26b-abliterated-multimodal is the smaller download — 16,796,016,032 bytes against 16,796,017,248.

From the file· summed bytes, KV per layer

	supergemma4-26b-abliterated-multimodal	gemma-4-26B-A4B-it
Parameters	25.8B	26.5B
Architecture	gemma4	gemma4
Layers	30	30
Native context	262,144	262,144
Mixture of experts	yes, 128 experts	yes, 128 experts
Quantizations published	1	46
Smallest quantization	15.64 GiB	8.99 GiB
Q4_K_M	15.64 GiB	15.64 GiB
Licence	gemma	apache-2.0

the term that decides long-context viability

Context	supergemma4-26b-abliterated-multimodal	gemma-4-26B-A4B-it	Ratio
4,096	0.45 GiB	0.45 GiB	1.00×
8,192	0.61 GiB	0.61 GiB	1.00×
16,384	0.92 GiB	0.92 GiB	1.00×
32,768	1.54 GiB	1.54 GiB	1.00×
65,536	2.79 GiB	2.79 GiB	1.00×
131,072	5.29 GiB	5.29 GiB	1.00×