Is Mixtral-8x7B-MoE-RP-Story or Qwen3-Coder-30B-A3B-Instruct smaller?

Qwen3-Coder-30B-A3B-Instruct is smaller at Q4_K_M: 17.28 GiB against 24.63 GiB.

Which uses less memory at long context?

Qwen3-Coder-30B-A3B-Instruct — its KV cache at 32K context is 1.3x smaller, because of how its attention layers cache.

Model comparison

Mixtral-8x7B-MoE-RP-Story vs Qwen3-Coder-30B-A3B-Instruct

At Q4_K_M, Qwen3-Coder-30B-A3B-Instruct is the smaller download — 18,556,689,568 bytes against 26,441,533,376. At long context the gap widens: Qwen3-Coder-30B-A3B-Instruct's KV cache at 32K is 1.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Mixtral-8x7B-MoE-RP-Story	Qwen3-Coder-30B-A3B-Instruct
Parameters	46.7B	30.5B
Architecture	llama	qwen3moe
Layers	32	48
Native context	32,768	262,144
Mixture of experts	yes, 8 experts	yes, 128 experts
Quantizations published	8	46
Smallest quantization	14.57 GiB	7.46 GiB
Q4_K_M	24.63 GiB	17.28 GiB
Licence	cc-by-nc-4.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Mixtral-8x7B-MoE-RP-Story	Qwen3-Coder-30B-A3B-Instruct	Ratio
4,096	0.50 GiB	0.38 GiB	1.33×
8,192	1.00 GiB	0.75 GiB	1.33×
16,384	2.00 GiB	1.50 GiB	1.33×
32,768	4.00 GiB	3.00 GiB	1.33×
65,536	8.00 GiB	6.00 GiB	1.33×
131,072	16.00 GiB	12.00 GiB	1.33×