Is gte-small or nomic-embed-text-v1 smaller?

gte-small is smaller at Q4_K_M: 0.03 GiB against 0.08 GiB.

Which uses less memory at long context?

gte-small — its KV cache at 32K context is 2.0x smaller, because of how its attention layers cache.

Model comparison

gte-small vs nomic-embed-text-v1

At Q4_K_M, gte-small is the smaller download — 29,203,744 bytes against 84,106,624. At long context the gap widens: gte-small's KV cache at 32K is 2.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	gte-small	nomic-embed-text-v1
Parameters	33M	137M
Architecture	bert	nomic-bert
Layers	12	12
Native context	512	8,192
Mixture of experts	no	no
Quantizations published	12	14
Smallest quantization	0.02 GiB	0.05 GiB
Q4_K_M	0.03 GiB	0.08 GiB
Licence	mit	apache-2.0

KV cache by context

the term that decides long-context viability

Context	gte-small	nomic-embed-text-v1	Ratio
4,096	0.07 GiB	0.14 GiB	2.00×
8,192	0.14 GiB	0.28 GiB	2.00×
16,384	0.28 GiB	0.56 GiB	2.00×
32,768	0.56 GiB	1.13 GiB	2.00×
65,536	1.13 GiB	2.25 GiB	2.00×
131,072	2.25 GiB	4.50 GiB	2.00×