Is Qwen3.8-27B or DeepSeek-R1-Distill-Qwen-14B-Uncensored smaller?

DeepSeek-R1-Distill-Qwen-14B-Uncensored is smaller at Q4_K_M: 8.37 GiB against 15.66 GiB.

Which uses less memory at long context?

Qwen3.8-27B — its KV cache at 32K context is 3.0x smaller, because of how its attention layers cache.

Model comparison

Qwen3.8-27B vs DeepSeek-R1-Distill-Qwen-14B-Uncensored

At Q4_K_M, DeepSeek-R1-Distill-Qwen-14B-Uncensored is the smaller download — 8,985,277,056 bytes against 16,810,714,336. At long context the gap widens: Qwen3.8-27B's KV cache at 32K is 3.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.8-27B	DeepSeek-R1-Distill-Qwen-14B-Uncensored
Parameters	27.8B	14.8B
Architecture	qwen35	qwen2
Layers	64	48
Native context	262,144	131,072
Mixture of experts	no	no
Quantizations published	22	46
Smallest quantization	8.39 GiB	3.36 GiB
Q4_K_M	15.66 GiB	8.37 GiB
Licence	apache-2.0	mit

KV cache by context

the term that decides long-context viability

Context	Qwen3.8-27B	DeepSeek-R1-Distill-Qwen-14B-Uncensored	Ratio
4,096	0.25 GiB	0.75 GiB	3.00×
8,192	0.50 GiB	1.50 GiB	3.00×
16,384	1.00 GiB	3.00 GiB	3.00×
32,768	2.00 GiB	6.00 GiB	3.00×
65,536	4.00 GiB	12.00 GiB	3.00×
131,072	8.00 GiB	24.00 GiB	3.00×