Is Assistant_Pepe_32B or Qwen3-30B-A3B-Thinking-2507 smaller?

Both publish quantizations; compare the table for the exact sizes.

Which uses less memory at long context?

Qwen3-30B-A3B-Thinking-2507 — its KV cache at 32K context is 2.7x smaller, because of how its attention layers cache.

Model comparison

Assistant_Pepe_32B vs Qwen3-30B-A3B-Thinking-2507

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: Qwen3-30B-A3B-Thinking-2507's KV cache at 32K is 2.7× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Assistant_Pepe_32B	Qwen3-30B-A3B-Thinking-2507
Parameters	32.8B	30.5B
Architecture	qwen3	qwen3moe
Layers	64	48
Native context	40,960	262,144
Mixture of experts	no	yes, 128 experts
Quantizations published	25	51
Smallest quantization	6.82 GiB	7.05 GiB
Q4_K_M	—	17.28 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Assistant_Pepe_32B	Qwen3-30B-A3B-Thinking-2507	Ratio
4,096	1.00 GiB	0.38 GiB	2.67×
8,192	2.00 GiB	0.75 GiB	2.67×
16,384	4.00 GiB	1.50 GiB	2.67×
32,768	8.00 GiB	3.00 GiB	2.67×
65,536	16.00 GiB	6.00 GiB	2.67×
131,072	32.00 GiB	12.00 GiB	2.67×