Is gemma-3-12b-it-vl-Deepseek-v3.1-Heretic-Uncensored-Thinking or Qwen3-8B smaller?

Qwen3-8B is smaller at Q4_K_M: 4.68 GiB against 6.80 GiB.

Which uses less memory at long context?

gemma-3-12b-it-vl-Deepseek-v3.1-Heretic-Uncensored-Thinking — its KV cache at 32K context is 1.8x smaller, because of how its attention layers cache.

Model comparison

gemma-3-12b-it-vl-Deepseek-v3.1-Heretic-Uncensored-Thinking vs Qwen3-8B

At Q4_K_M, Qwen3-8B is the smaller download — 5,027,783,488 bytes against 7,300,779,968. At long context the gap widens: gemma-3-12b-it-vl-Deepseek-v3.1-Heretic-Uncensored-Thinking's KV cache at 32K is 1.8× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	gemma-3-12b-it-vl-Deepseek-v3.1-Heretic-Uncensored-Thinking	Qwen3-8B
Parameters	12.2B	8.2B
Architecture	gemma3	qwen3
Layers	48	36
Native context	131,072	40,960
Mixture of experts	no	no
Quantizations published	35	51
Smallest quantization	2.74 GiB	2.12 GiB
Q4_K_M	6.80 GiB	4.68 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	gemma-3-12b-it-vl-Deepseek-v3.1-Heretic-Uncensored-Thinking	Qwen3-8B	Ratio
4,096	0.72 GiB	0.56 GiB	1.28×
8,192	0.97 GiB	1.13 GiB	1.16×
16,384	1.47 GiB	2.25 GiB	1.53×
32,768	2.47 GiB	4.50 GiB	1.82×
65,536	4.47 GiB	9.00 GiB	2.01×
131,072	8.47 GiB	18.00 GiB	2.13×