Is llama3-8B-DarkIdol-2.3-Uncensored-32K or Qwen3-4B smaller?

Qwen3-4B is smaller at Q4_K_M: 2.33 GiB against 4.58 GiB.

Which uses less memory at long context?

llama3-8B-DarkIdol-2.3-Uncensored-32K — its KV cache at 32K context is 1.1x smaller, because of how its attention layers cache.

Model comparison

At Q4_K_M, Qwen3-4B is the smaller download — 2,497,280,256 bytes against 4,920,734,496.

From the file· summed bytes, KV per layer

	llama3-8B-DarkIdol-2.3-Uncensored-32K	Qwen3-4B
Parameters	8.0B	4.0B
Architecture	llama	qwen3
Layers	32	36
Native context	131,072	40,960
Mixture of experts	no	no
Quantizations published	36	29
Smallest quantization	1.88 GiB	1.01 GiB
Q4_K_M	4.58 GiB	2.33 GiB
Licence	llama3	—

the term that decides long-context viability

Context	llama3-8B-DarkIdol-2.3-Uncensored-32K	Qwen3-4B	Ratio
4,096	0.50 GiB	0.56 GiB	1.13×
8,192	1.00 GiB	1.13 GiB	1.13×
16,384	2.00 GiB	2.25 GiB	1.13×
32,768	4.00 GiB	4.50 GiB	1.13×
65,536	8.00 GiB	9.00 GiB	1.13×
131,072	16.00 GiB	18.00 GiB	1.13×