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

mxbai-embed-xsmall-v1 vs gte-small

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

	mxbai-embed-xsmall-v1	gte-small
Parameters	24M	33M
Architecture	bert	bert
Layers	6	12
Native context	4,096	512
Mixture of experts	no	no
Quantizations published	4	12
Smallest quantization	0.03 GiB	0.02 GiB
Q4_K_M	—	0.03 GiB
Licence	apache-2.0	mit

KV cache by context

the term that decides long-context viability

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