Is gte-large or jina-embeddings-v5-text-small smaller?

gte-large is smaller at Q4_K_M: 0.20 GiB against 0.37 GiB.

Which uses less memory at long context?

gte-large — its KV cache at 32K context is 1.2x smaller, because of how its attention layers cache.

Model comparison

gte-large vs jina-embeddings-v5-text-small

At Q4_K_M, gte-large is the smaller download — 215,891,488 bytes against 396,705,152. At long context the gap widens: gte-large's KV cache at 32K is 1.2× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	gte-large	jina-embeddings-v5-text-small
Parameters	335M	596M
Architecture	bert	qwen3
Layers	24	28
Native context	512	32,768
Mixture of experts	no	no
Quantizations published	12	56
Smallest quantization	0.13 GiB	0.19 GiB
Q4_K_M	0.20 GiB	0.37 GiB
Licence	mit	cc-by-nc-4.0

KV cache by context

the term that decides long-context viability

Context	gte-large	jina-embeddings-v5-text-small	Ratio
4,096	0.38 GiB	0.44 GiB	1.17×
8,192	0.75 GiB	0.88 GiB	1.17×
16,384	1.50 GiB	1.75 GiB	1.17×
32,768	3.00 GiB	3.50 GiB	1.17×
65,536	6.00 GiB	7.00 GiB	1.17×
131,072	12.00 GiB	14.00 GiB	1.17×