Is Godoter-27B or Qwen3-30B-A3B-Thinking-2507 smaller?

Godoter-27B is smaller at Q4_K_M: 15.41 GiB against 17.28 GiB.

Which uses less memory at long context?

Godoter-27B — its KV cache at 32K context is 1.5x smaller, because of how its attention layers cache.

Model comparison

Godoter-27B vs Qwen3-30B-A3B-Thinking-2507

At Q4_K_M, Godoter-27B is the smaller download — 16,547,398,976 bytes against 18,556,685,824. At long context the gap widens: Godoter-27B'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

	Godoter-27B	Qwen3-30B-A3B-Thinking-2507
Parameters	27.8B	30.5B
Architecture	qwen35	qwen3moe
Layers	64	48
Native context	262,144	262,144
Mixture of experts	no	yes, 128 experts
Quantizations published	28	51
Smallest quantization	10.12 GiB	7.05 GiB
Q4_K_M	15.41 GiB	17.28 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Godoter-27B	Qwen3-30B-A3B-Thinking-2507	Ratio
4,096	0.25 GiB	0.38 GiB	1.50×
8,192	0.50 GiB	0.75 GiB	1.50×
16,384	1.00 GiB	1.50 GiB	1.50×
32,768	2.00 GiB	3.00 GiB	1.50×
65,536	4.00 GiB	6.00 GiB	1.50×
131,072	8.00 GiB	12.00 GiB	1.50×