Is Qwen3.5-4B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING or HyperCLOVAX-SEED-Text-Instruct-1.5B smaller?

HyperCLOVAX-SEED-Text-Instruct-1.5B is smaller at Q4_K_M: 1.06 GiB against 2.52 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We cannot resolve the KV layout for one of these models, so we do not publish a comparison.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 2,707,515,520.

From the file· summed bytes, KV per layer

	Qwen3.5-4B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING	HyperCLOVAX-SEED-Text-Instruct-1.5B
Parameters	4.5B	1.6B
Architecture	qwen35	llama
Layers	32	—
Native context	262,144	—
Mixture of experts	no	no
Quantizations published	36	1
Smallest quantization	1.09 GiB	1.06 GiB
Q4_K_M	2.52 GiB	1.06 GiB
Licence	apache-2.0	other

the term that decides long-context viability

Context	Qwen3.5-4B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING	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	—	—