Is Qwen3-Coder-30B-A3B-Instruct or Nous-Hermes-Llama2-70b smaller?

Qwen3-Coder-30B-A3B-Instruct is smaller at Q4_K_M: 17.28 GiB against 38.58 GiB.

Which uses less memory at long context?

Qwen3-Coder-30B-A3B-Instruct — its KV cache at 32K context is 3.3x smaller, because of how its attention layers cache.

Model comparison

Qwen3-Coder-30B-A3B-Instruct vs Nous-Hermes-Llama2-70b

At Q4_K_M, Qwen3-Coder-30B-A3B-Instruct is the smaller download — 18,556,689,568 bytes against 41,422,921,728. At long context the gap widens: Qwen3-Coder-30B-A3B-Instruct's KV cache at 32K is 3.3× 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	Nous-Hermes-Llama2-70b
Parameters	30.5B	69.0B
Architecture	qwen3moe	llama
Layers	48	80
Native context	262,144	4,096
Mixture of experts	yes, 128 experts	no
Quantizations published	46	30
Smallest quantization	7.46 GiB	13.54 GiB
Q4_K_M	17.28 GiB	38.58 GiB
Licence	apache-2.0	mit

KV cache by context

the term that decides long-context viability

Context	Qwen3-Coder-30B-A3B-Instruct	Nous-Hermes-Llama2-70b	Ratio
4,096	0.38 GiB	1.25 GiB	3.33×
8,192	0.75 GiB	2.50 GiB	3.33×
16,384	1.50 GiB	5.00 GiB	3.33×
32,768	3.00 GiB	10.00 GiB	3.33×
65,536	6.00 GiB	20.00 GiB	3.33×
131,072	12.00 GiB	40.00 GiB	3.33×