Is Kuwutu-7B-CYOA-v2 or HyperCLOVAX-SEED-Text-Instruct-1.5B smaller?

HyperCLOVAX-SEED-Text-Instruct-1.5B is smaller at Q4_K_M: 1.06 GiB against 4.37 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We cannot resolve the KV layout for one of these models, so we do not publish a comparison.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 4,693,775,488.

From the file· summed bytes, KV per layer

	Kuwutu-7B-CYOA-v2	HyperCLOVAX-SEED-Text-Instruct-1.5B
Parameters	7.6B	1.6B
Architecture	qwen2	llama
Layers	36	—
Native context	32,768	—
Mixture of experts	no	no
Quantizations published	33	1
Smallest quantization	1.86 GiB	1.06 GiB
Q4_K_M	4.37 GiB	1.06 GiB
Licence	cc-by-nc-4.0	other

the term that decides long-context viability

Context	Kuwutu-7B-CYOA-v2	HyperCLOVAX-SEED-Text-Instruct-1.5B	Ratio
4,096	0.56 GiB	—	—
8,192	1.13 GiB	—	—
16,384	2.25 GiB	—	—
32,768	4.50 GiB	—	—
65,536	9.00 GiB	—	—
131,072	18.00 GiB	—	—