Is OLMoE-1B-7B-0924-Instruct or gemma-4-E4B-it smaller?

OLMoE-1B-7B-0924-Instruct is smaller at Q4_K_M: 3.92 GiB against 4.64 GiB.

Which uses less memory at long context?

gemma-4-E4B-it — its KV cache at 32K context is 7.9x smaller, because of how its attention layers cache.

Model comparison

OLMoE-1B-7B-0924-Instruct vs gemma-4-E4B-it

At Q4_K_M, OLMoE-1B-7B-0924-Instruct is the smaller download — 4,213,512,672 bytes against 4,977,171,584. At long context the gap widens: gemma-4-E4B-it's KV cache at 32K is 7.9× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	OLMoE-1B-7B-0924-Instruct	gemma-4-E4B-it
Parameters	6.9B	8.0B
Architecture	olmoe	gemma4
Layers	16	42
Native context	4,096	131,072
Mixture of experts	yes, 64 experts	no
Quantizations published	54	36
Smallest quantization	1.39 GiB	3.30 GiB
Q4_K_M	3.92 GiB	4.64 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	OLMoE-1B-7B-0924-Instruct	gemma-4-E4B-it	Ratio
4,096	0.50 GiB	0.12 GiB	4.06×
8,192	1.00 GiB	0.18 GiB	5.63×
16,384	2.00 GiB	0.29 GiB	6.97×
32,768	4.00 GiB	0.51 GiB	7.91×
65,536	8.00 GiB	0.94 GiB	8.48×
131,072	16.00 GiB	1.82 GiB	8.80×