Is Dolphin3.0-Llama3.2-1B or HyperCLOVAX-SEED-Text-Instruct-1.5B smaller?

Dolphin3.0-Llama3.2-1B is smaller at Q4_K_M: 0.75 GiB against 1.06 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We cannot resolve the KV layout for one of these models, so we do not publish a comparison.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, Dolphin3.0-Llama3.2-1B is the smaller download — 807,697,440 bytes against 1,133,974,368.

From the file· summed bytes, KV per layer

	Dolphin3.0-Llama3.2-1B	HyperCLOVAX-SEED-Text-Instruct-1.5B
Parameters	1.2B	1.6B
Architecture	llama	llama
Layers	16	—
Native context	131,072	—
Mixture of experts	no	no
Quantizations published	23	1
Smallest quantization	0.48 GiB	1.06 GiB
Q4_K_M	0.75 GiB	1.06 GiB
Licence	llama3.2	other

the term that decides long-context viability

Context	Dolphin3.0-Llama3.2-1B	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	—	—