Is gte-small or mxbai-embed-xsmall-v1 smaller?

Both publish quantizations; compare the table for the exact sizes.

Which uses less memory at long context?

mxbai-embed-xsmall-v1 — its KV cache at 32K context is 2.0x smaller, because of how its attention layers cache.

Model comparison

gte-small vs mxbai-embed-xsmall-v1

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: mxbai-embed-xsmall-v1'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	mxbai-embed-xsmall-v1
Parameters	33M	24M
Architecture	bert	bert
Layers	12	6
Native context	512	4,096
Mixture of experts	no	no
Quantizations published	12	4
Smallest quantization	0.02 GiB	0.03 GiB
Q4_K_M	0.03 GiB	—
Licence	mit	apache-2.0

KV cache by context

the term that decides long-context viability

Context	gte-small	mxbai-embed-xsmall-v1	Ratio
4,096	0.07 GiB	0.04 GiB	2.00×
8,192	0.14 GiB	0.07 GiB	2.00×
16,384	0.28 GiB	0.14 GiB	2.00×
32,768	0.56 GiB	0.28 GiB	2.00×
65,536	1.13 GiB	0.56 GiB	2.00×
131,072	2.25 GiB	1.13 GiB	2.00×