Is Surogate-3.5-4B or HyperCLOVAX-SEED-Text-Instruct-1.5B smaller?

HyperCLOVAX-SEED-Text-Instruct-1.5B is smaller at Q4_K_M: 1.06 GiB against 2.59 GiB.

Which uses less memory at long context?

We cannot resolve the KV layout for one of these models, so we do not publish a comparison.

Model comparison

At Q4_K_M, HyperCLOVAX-SEED-Text-Instruct-1.5B is the smaller download — 1,133,974,368 bytes against 2,783,447,104.

From the file· summed bytes, KV per layer

	Surogate-3.5-4B	HyperCLOVAX-SEED-Text-Instruct-1.5B
Parameters	5.3B	1.6B
Architecture	qwen35	llama
Layers	32	—
Native context	262,144	—
Mixture of experts	no	no
Quantizations published	27	1
Smallest quantization	1.82 GiB	1.06 GiB
Q4_K_M	2.59 GiB	1.06 GiB
Licence	apache-2.0	other

the term that decides long-context viability

Context	Surogate-3.5-4B	HyperCLOVAX-SEED-Text-Instruct-1.5B	Ratio
4,096	0.13 GiB	—	—
8,192	0.25 GiB	—	—
16,384	0.50 GiB	—	—
32,768	1.00 GiB	—	—
65,536	2.00 GiB	—	—
131,072	4.00 GiB	—	—