Is EXAONE-4.0-1.2B-abliterated or gemma-3-1b-it smaller?

gemma-3-1b-it is smaller at Q4_K_M: 0.75 GiB against 0.87 GiB.

Which uses less memory at long context?

gemma-3-1b-it — its KV cache at 32K context is 12.8x smaller, because of how its attention layers cache.

Model comparison

EXAONE-4.0-1.2B-abliterated vs gemma-3-1b-it

At Q4_K_M, gemma-3-1b-it is the smaller download — 806,058,240 bytes against 930,403,456. At long context the gap widens: gemma-3-1b-it's KV cache at 32K is 12.8× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	EXAONE-4.0-1.2B-abliterated	gemma-3-1b-it
Parameters	1.5B	1000M
Architecture	exaone4	gemma3
Layers	30	26
Native context	65,536	32,768
Mixture of experts	no	no
Quantizations published	36	28
Smallest quantization	0.42 GiB	0.52 GiB
Q4_K_M	0.87 GiB	0.75 GiB
Licence	—	gemma

KV cache by context

the term that decides long-context viability

Context	EXAONE-4.0-1.2B-abliterated	gemma-3-1b-it	Ratio
4,096	0.23 GiB	0.04 GiB	6.32×
8,192	0.47 GiB	0.05 GiB	8.89×
16,384	0.94 GiB	0.08 GiB	11.16×
32,768	1.88 GiB	0.15 GiB	12.80×
65,536	3.75 GiB	0.27 GiB	13.81×
131,072	7.50 GiB	0.52 GiB	14.38×