Is granite-4.0-h-micro or HyperCLOVAX-SEED-Text-Instruct-1.5B smaller?

HyperCLOVAX-SEED-Text-Instruct-1.5B is smaller at Q4_K_M: 1.06 GiB against 1.81 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We cannot resolve the KV layout for one of these models, so we do not publish a comparison.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 1,942,564,480.

From the file· summed bytes, KV per layer

	granite-4.0-h-micro	HyperCLOVAX-SEED-Text-Instruct-1.5B
Parameters	3.2B	1.6B
Architecture	granitehybrid	llama
Layers	40	—
Native context	131,072	—
Mixture of experts	no	no
Quantizations published	58	1
Smallest quantization	0.72 GiB	1.06 GiB
Q4_K_M	1.81 GiB	1.06 GiB
Licence	apache-2.0	other

the term that decides long-context viability

Context	granite-4.0-h-micro	HyperCLOVAX-SEED-Text-Instruct-1.5B	Ratio
4,096	0.03 GiB	—	—
8,192	0.06 GiB	—	—
16,384	0.13 GiB	—	—
32,768	0.25 GiB	—	—
65,536	0.50 GiB	—	—
131,072	1.00 GiB	—	—