Is ZAYA1-8B-Coder or Qwen3-30B-A3B-Thinking-2507 smaller?

ZAYA1-8B-Coder is smaller at Q4_K_M: 5.19 GiB against 17.28 GiB.

Which uses less memory at long context?

ZAYA1-8B-Coder — its KV cache at 32K context is 1.2x smaller, because of how its attention layers cache.

Model comparison

ZAYA1-8B-Coder vs Qwen3-30B-A3B-Thinking-2507

At Q4_K_M, ZAYA1-8B-Coder is the smaller download — 5,567,581,024 bytes against 18,556,685,824. At long context the gap widens: ZAYA1-8B-Coder's KV cache at 32K is 1.2× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	ZAYA1-8B-Coder	Qwen3-30B-A3B-Thinking-2507
Parameters	8.8B	30.5B
Architecture	zaya	qwen3moe
Layers	80	48
Native context	131,072	262,144
Mixture of experts	yes, 16 experts	yes, 128 experts
Quantizations published	3	51
Smallest quantization	5.19 GiB	7.05 GiB
Q4_K_M	5.19 GiB	17.28 GiB
Licence	—	apache-2.0

KV cache by context

the term that decides long-context viability

Context	ZAYA1-8B-Coder	Qwen3-30B-A3B-Thinking-2507	Ratio
4,096	0.31 GiB	0.38 GiB	1.20×
8,192	0.63 GiB	0.75 GiB	1.20×
16,384	1.25 GiB	1.50 GiB	1.20×
32,768	2.50 GiB	3.00 GiB	1.20×
65,536	5.00 GiB	6.00 GiB	1.20×
131,072	10.00 GiB	12.00 GiB	1.20×