Is ZAYA1-8B or gemma-4-E4B-it smaller?

gemma-4-E4B-it is smaller at Q4_K_M: 4.64 GiB against 5.19 GiB.

Which uses less memory at long context?

ZAYA1-8B — its KV cache at 32K context is 13260.8x smaller, because of how its attention layers cache.

Model comparison

ZAYA1-8B vs gemma-4-E4B-it

At Q4_K_M, gemma-4-E4B-it is the smaller download — 4,977,171,584 bytes against 5,567,581,549. At long context the gap widens: ZAYA1-8B's KV cache at 32K is 13260.8× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	ZAYA1-8B	gemma-4-E4B-it
Parameters	8.8B	8.0B
Architecture	zaya	gemma4
Layers	40	42
Native context	131,072	131,072
Mixture of experts	yes, 16 experts	no
Quantizations published	6	36
Smallest quantization	4.20 GiB	3.30 GiB
Q4_K_M	5.19 GiB	4.64 GiB
Licence	—	apache-2.0

KV cache by context

the term that decides long-context viability

Context	gemma-4-E4B-it	Ratio
4,096	0.12 GiB	3225.60×
8,192	0.18 GiB	4659.20×
16,384	0.29 GiB	7526.40×
32,768	0.51 GiB	13260.80×
65,536	0.94 GiB	24729.60×
131,072	1.82 GiB	47667.20×