Is Assistant_Pepe_70B or Qwen3-30B-A3B-Thinking-2507 smaller?

Qwen3-30B-A3B-Thinking-2507 is smaller at Q4_K_M: 17.28 GiB against 39.60 GiB.

Which uses less memory at long context?

Qwen3-30B-A3B-Thinking-2507 — its KV cache at 32K context is 3.3x smaller, because of how its attention layers cache.

Model comparison

Assistant_Pepe_70B vs Qwen3-30B-A3B-Thinking-2507

At Q4_K_M, Qwen3-30B-A3B-Thinking-2507 is the smaller download — 18,556,685,824 bytes against 42,520,393,952. At long context the gap widens: Qwen3-30B-A3B-Thinking-2507'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

	Assistant_Pepe_70B	Qwen3-30B-A3B-Thinking-2507
Parameters	70.6B	30.5B
Architecture	llama	qwen3moe
Layers	80	48
Native context	131,072	262,144
Mixture of experts	no	yes, 128 experts
Quantizations published	55	51
Smallest quantization	14.29 GiB	7.05 GiB
Q4_K_M	39.60 GiB	17.28 GiB
Licence	llama3.1	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Assistant_Pepe_70B	Qwen3-30B-A3B-Thinking-2507	Ratio
4,096	1.25 GiB	0.38 GiB	3.33×
8,192	2.50 GiB	0.75 GiB	3.33×
16,384	5.00 GiB	1.50 GiB	3.33×
32,768	10.00 GiB	3.00 GiB	3.33×
65,536	20.00 GiB	6.00 GiB	3.33×
131,072	40.00 GiB	12.00 GiB	3.33×