Is Gemma-The-Writer-N-Restless-Quill-10B-Uncensored or Qwen3-4B smaller?

Qwen3-4B is smaller at Q4_K_M: 2.33 GiB against 5.68 GiB.

Which uses less memory at long context?

Qwen3-4B — its KV cache at 32K context is 1.5x smaller, because of how its attention layers cache.

Model comparison

Gemma-The-Writer-N-Restless-Quill-10B-Uncensored vs Qwen3-4B

At Q4_K_M, Qwen3-4B is the smaller download — 2,497,280,256 bytes against 6,100,479,520. At long context the gap widens: Qwen3-4B's KV cache at 32K is 1.5× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Gemma-The-Writer-N-Restless-Quill-10B-Uncensored	Qwen3-4B
Parameters	10.0B	4.0B
Architecture	gemma2	qwen3
Layers	46	36
Native context	8,192	40,960
Mixture of experts	no	no
Quantizations published	31	29
Smallest quantization	2.37 GiB	1.01 GiB
Q4_K_M	5.68 GiB	2.33 GiB
Licence	apache-2.0	—

KV cache by context

the term that decides long-context viability

Context	Gemma-The-Writer-N-Restless-Quill-10B-Uncensored	Qwen3-4B	Ratio
4,096	1.44 GiB	0.56 GiB	2.56×
8,192	2.25 GiB	1.13 GiB	2.00×
16,384	3.68 GiB	2.25 GiB	1.64×
32,768	6.56 GiB	4.50 GiB	1.46×
65,536	12.31 GiB	9.00 GiB	1.37×
131,072	23.81 GiB	18.00 GiB	1.32×