Is Llama-3.2-3B-Instruct-roleplay-tuned or HyperCLOVAX-SEED-Text-Instruct-1.5B smaller?

HyperCLOVAX-SEED-Text-Instruct-1.5B is smaller at Q4_K_M: 1.06 GiB against 1.88 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We cannot resolve the KV layout for one of these models, so we do not publish a comparison.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 2,019,378,752.

From the file· summed bytes, KV per layer

	Llama-3.2-3B-Instruct-roleplay-tuned	HyperCLOVAX-SEED-Text-Instruct-1.5B
Parameters	3.2B	1.6B
Architecture	llama	llama
Layers	28	—
Native context	131,072	—
Mixture of experts	no	no
Quantizations published	36	1
Smallest quantization	0.81 GiB	1.06 GiB
Q4_K_M	1.88 GiB	1.06 GiB
Licence	llama3.2	other

the term that decides long-context viability

Context	Llama-3.2-3B-Instruct-roleplay-tuned	HyperCLOVAX-SEED-Text-Instruct-1.5B	Ratio
4,096	0.44 GiB	—	—
8,192	0.88 GiB	—	—
16,384	1.75 GiB	—	—
32,768	3.50 GiB	—	—
65,536	7.00 GiB	—	—
131,072	14.00 GiB	—	—