Is gemma-4-26B-A4B-it-local-abliterated-sota-internal-t34 or Qwen3-30B-A3B-Thinking-2507 smaller?

Both publish quantizations; compare the table for the exact sizes.

Which uses less memory at long context?

gemma-4-26B-A4B-it-local-abliterated-sota-internal-t34 — its KV cache at 32K context is 1.9x smaller, because of how its attention layers cache.

Model comparison

gemma-4-26B-A4B-it-local-abliterated-sota-internal-t34 vs Qwen3-30B-A3B-Thinking-2507

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: gemma-4-26B-A4B-it-local-abliterated-sota-internal-t34's KV cache at 32K is 1.9× 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-local-abliterated-sota-internal-t34	Qwen3-30B-A3B-Thinking-2507
Parameters	25.8B	30.5B
Architecture	gemma4	qwen3moe
Layers	30	48
Native context	262,144	262,144
Mixture of experts	yes, 128 experts	yes, 128 experts
Quantizations published	23	51
Smallest quantization	7.72 GiB	7.05 GiB
Q4_K_M	—	17.28 GiB
Licence	gemma	apache-2.0

KV cache by context

the term that decides long-context viability

Context	gemma-4-26B-A4B-it-local-abliterated-sota-internal-t34	Qwen3-30B-A3B-Thinking-2507	Ratio
4,096	0.45 GiB	0.38 GiB	1.20×
8,192	0.61 GiB	0.75 GiB	1.24×
16,384	0.92 GiB	1.50 GiB	1.63×
32,768	1.54 GiB	3.00 GiB	1.94×
65,536	2.79 GiB	6.00 GiB	2.15×
131,072	5.29 GiB	12.00 GiB	2.27×