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

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

Which uses less memory at long context?

ZAYA1-8B — its KV cache at 32K context is 78643.2x smaller, because of how its attention layers cache.

Model comparison

Qwen3-Coder-30B-A3B-Instruct vs ZAYA1-8B

At Q4_K_M, ZAYA1-8B is the smaller download — 5,567,581,549 bytes against 18,556,689,568. At long context the gap widens: ZAYA1-8B's KV cache at 32K is 78643.2× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3-Coder-30B-A3B-Instruct	ZAYA1-8B
Parameters	30.5B	8.8B
Architecture	qwen3moe	zaya
Layers	48	40
Native context	262,144	131,072
Mixture of experts	yes, 128 experts	yes, 16 experts
Quantizations published	46	6
Smallest quantization	7.46 GiB	4.20 GiB
Q4_K_M	17.28 GiB	5.19 GiB
Licence	apache-2.0	—

KV cache by context

the term that decides long-context viability

Context	Qwen3-Coder-30B-A3B-Instruct	Ratio
4,096	0.38 GiB	9830.40×
8,192	0.75 GiB	19660.80×
16,384	1.50 GiB	39321.60×
32,768	3.00 GiB	78643.20×
65,536	6.00 GiB	157286.40×
131,072	12.00 GiB	314572.80×