Is Qwen3-Coder-30B-A3B-Instruct or Mixtral-8x7B-v0.1 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

Qwen3-Coder-30B-A3B-Instruct vs Mixtral-8x7B-v0.1

At Q4_K_M, Qwen3-Coder-30B-A3B-Instruct is the smaller download — 18,556,689,568 bytes against 26,441,532,864. 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

	Qwen3-Coder-30B-A3B-Instruct	Mixtral-8x7B-v0.1
Parameters	30.5B	46.7B
Architecture	qwen3moe	llama
Layers	48	32
Native context	262,144	32,768
Mixture of experts	yes, 128 experts	yes, 8 experts
Quantizations published	46	36
Smallest quantization	7.46 GiB	14.57 GiB
Q4_K_M	17.28 GiB	24.63 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3-Coder-30B-A3B-Instruct	Mixtral-8x7B-v0.1	Ratio
4,096	0.38 GiB	0.50 GiB	1.33×
8,192	0.75 GiB	1.00 GiB	1.33×
16,384	1.50 GiB	2.00 GiB	1.33×
32,768	3.00 GiB	4.00 GiB	1.33×
65,536	6.00 GiB	8.00 GiB	1.33×
131,072	12.00 GiB	16.00 GiB	1.33×