Is gemma-4-26B-A4B-it or Qwen3-VL-32B-Instruct-ultra-uncensored-heretic smaller?

gemma-4-26B-A4B-it is smaller at Q4_K_M: 15.64 GiB against 18.40 GiB.

Which uses less memory at long context?

gemma-4-26B-A4B-it — its KV cache at 32K context is 5.2x smaller, because of how its attention layers cache.

Model comparison

gemma-4-26B-A4B-it vs Qwen3-VL-32B-Instruct-ultra-uncensored-heretic

At Q4_K_M, gemma-4-26B-A4B-it is the smaller download — 16,796,017,248 bytes against 19,762,151,392. At long context the gap widens: gemma-4-26B-A4B-it's KV cache at 32K is 5.2× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	gemma-4-26B-A4B-it	Qwen3-VL-32B-Instruct-ultra-uncensored-heretic
Parameters	26.5B	33.4B
Architecture	gemma4	qwen3vl
Layers	30	64
Native context	262,144	262,144
Mixture of experts	yes, 128 experts	no
Quantizations published	46	43
Smallest quantization	8.99 GiB	6.82 GiB
Q4_K_M	15.64 GiB	18.40 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	gemma-4-26B-A4B-it	Qwen3-VL-32B-Instruct-ultra-uncensored-heretic	Ratio
4,096	0.45 GiB	1.00 GiB	2.23×
8,192	0.61 GiB	2.00 GiB	3.30×
16,384	0.92 GiB	4.00 GiB	4.36×
32,768	1.54 GiB	8.00 GiB	5.18×
65,536	2.79 GiB	16.00 GiB	5.73×
131,072	5.29 GiB	32.00 GiB	6.05×