Is Qwen3-14B-GPT-5.2-High-Reasoning-Distill or Qwen3-8B smaller?

Qwen3-8B is smaller at Q4_K_M: 4.68 GiB against 16.77 GiB.

Which uses less memory at long context?

Qwen3-8B — its KV cache at 32K context is 1.1x smaller, because of how its attention layers cache.

Model comparison

At Q4_K_M, Qwen3-8B is the smaller download — 5,027,783,488 bytes against 18,003,508,096.

From the file· summed bytes, KV per layer

	Qwen3-14B-GPT-5.2-High-Reasoning-Distill	Qwen3-8B
Parameters	14.8B	8.2B
Architecture	qwen3	qwen3
Layers	40	36
Native context	40,960	40,960
Mixture of experts	no	no
Quantizations published	11	51
Smallest quantization	2.82 GiB	2.12 GiB
Q4_K_M	16.77 GiB	4.68 GiB
Licence	—	apache-2.0

the term that decides long-context viability

Context	Qwen3-14B-GPT-5.2-High-Reasoning-Distill	Qwen3-8B	Ratio
4,096	0.63 GiB	0.56 GiB	1.11×
8,192	1.25 GiB	1.13 GiB	1.11×
16,384	2.50 GiB	2.25 GiB	1.11×
32,768	5.00 GiB	4.50 GiB	1.11×
65,536	10.00 GiB	9.00 GiB	1.11×
131,072	20.00 GiB	18.00 GiB	1.11×