Is UncensoredLM-DeepSeek-R1-Distill-Qwen-14B or gemma-4-E4B-it smaller?

gemma-4-E4B-it is smaller at Q4_K_M: 4.64 GiB against 8.05 GiB.

Which uses less memory at long context?

gemma-4-E4B-it — its KV cache at 32K context is 11.4x smaller, because of how its attention layers cache.

Model comparison

UncensoredLM-DeepSeek-R1-Distill-Qwen-14B vs gemma-4-E4B-it

At Q4_K_M, gemma-4-E4B-it is the smaller download — 4,977,171,584 bytes against 8,639,113,408. At long context the gap widens: gemma-4-E4B-it's KV cache at 32K is 11.4× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	UncensoredLM-DeepSeek-R1-Distill-Qwen-14B	gemma-4-E4B-it
Parameters	14.2B	8.0B
Architecture	qwen2	gemma4
Layers	46	42
Native context	131,072	131,072
Mixture of experts	no	no
Quantizations published	25	36
Smallest quantization	4.23 GiB	3.30 GiB
Q4_K_M	8.05 GiB	4.64 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	UncensoredLM-DeepSeek-R1-Distill-Qwen-14B	gemma-4-E4B-it	Ratio
4,096	0.72 GiB	0.12 GiB	5.84×
8,192	1.44 GiB	0.18 GiB	8.09×
16,384	2.88 GiB	0.29 GiB	10.01×
32,768	5.75 GiB	0.51 GiB	11.37×
65,536	11.50 GiB	0.94 GiB	12.19×
131,072	23.00 GiB	1.82 GiB	12.65×