Is Gemma-3-4B-VL-it-Gemini-Pro-Heretic-Uncensored-Thinking or Qwen3.5-9B smaller?

Gemma-3-4B-VL-it-Gemini-Pro-Heretic-Uncensored-Thinking is smaller at Q4_K_M: 2.32 GiB against 5.24 GiB.

Which uses less memory at long context?

Gemma-3-4B-VL-it-Gemini-Pro-Heretic-Uncensored-Thinking — its KV cache at 32K context is 1.3x smaller, because of how its attention layers cache.

Model comparison

Gemma-3-4B-VL-it-Gemini-Pro-Heretic-Uncensored-Thinking vs Qwen3.5-9B

At Q4_K_M, Gemma-3-4B-VL-it-Gemini-Pro-Heretic-Uncensored-Thinking is the smaller download — 2,489,895,200 bytes against 5,627,044,256. At long context the gap widens: Gemma-3-4B-VL-it-Gemini-Pro-Heretic-Uncensored-Thinking's KV cache at 32K is 1.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Gemma-3-4B-VL-it-Gemini-Pro-Heretic-Uncensored-Thinking	Qwen3.5-9B
Parameters	4.3B	9.7B
Architecture	gemma3	qwen35
Layers	34	32
Native context	131,072	262,144
Mixture of experts	no	no
Quantizations published	12	34
Smallest quantization	1.61 GiB	2.97 GiB
Q4_K_M	2.32 GiB	5.24 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Gemma-3-4B-VL-it-Gemini-Pro-Heretic-Uncensored-Thinking	Qwen3.5-9B	Ratio
4,096	0.25 GiB	0.13 GiB	1.98×
8,192	0.33 GiB	0.25 GiB	1.30×
16,384	0.48 GiB	0.50 GiB	1.04×
32,768	0.79 GiB	1.00 GiB	1.26×
65,536	1.42 GiB	2.00 GiB	1.41×
131,072	2.67 GiB	4.00 GiB	1.50×