Is granite-4.1-3b or HyperCLOVAX-SEED-Text-Instruct-1.5B smaller?

HyperCLOVAX-SEED-Text-Instruct-1.5B is smaller at Q4_K_M: 1.06 GiB against 1.96 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We cannot resolve the KV layout for one of these models, so we do not publish a comparison.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 2,099,501,664.

From the file· summed bytes, KV per layer

	granite-4.1-3b	HyperCLOVAX-SEED-Text-Instruct-1.5B
Parameters	3.4B	1.6B
Architecture	granite	llama
Layers	40	—
Native context	131,072	—
Mixture of experts	no	no
Quantizations published	30	1
Smallest quantization	1.20 GiB	1.06 GiB
Q4_K_M	1.96 GiB	1.06 GiB
Licence	apache-2.0	other

the term that decides long-context viability

Context	granite-4.1-3b	HyperCLOVAX-SEED-Text-Instruct-1.5B	Ratio
4,096	0.31 GiB	—	—
8,192	0.63 GiB	—	—
16,384	1.25 GiB	—	—
32,768	2.50 GiB	—	—
65,536	5.00 GiB	—	—
131,072	10.00 GiB	—	—