Is Qwen3.6-35B-REAP-Pruned-ratio-0.5 or Qwen3.6-27B smaller?

Qwen3.6-35B-REAP-Pruned-ratio-0.5 is smaller at Q4_K_M: 10.59 GiB against 15.41 GiB.

Which uses less memory at long context?

Qwen3.6-35B-REAP-Pruned-ratio-0.5 — its KV cache at 32K context is 3.2x smaller, because of how its attention layers cache.

Model comparison

Qwen3.6-35B-REAP-Pruned-ratio-0.5 vs Qwen3.6-27B

At Q4_K_M, Qwen3.6-35B-REAP-Pruned-ratio-0.5 is the smaller download — 11,373,050,592 bytes against 16,547,397,888. At long context the gap widens: Qwen3.6-35B-REAP-Pruned-ratio-0.5's KV cache at 32K is 3.2× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.6-35B-REAP-Pruned-ratio-0.5	Qwen3.6-27B
Parameters	19.0B	27.8B
Architecture	qwen35moe	qwen35
Layers	40	64
Native context	262,144	262,144
Mixture of experts	yes, 128 experts	no
Quantizations published	2	40
Smallest quantization	10.59 GiB	8.74 GiB
Q4_K_M	10.59 GiB	15.41 GiB
Licence	—	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.6-35B-REAP-Pruned-ratio-0.5	Qwen3.6-27B	Ratio
4,096	0.08 GiB	0.25 GiB	3.20×
8,192	0.16 GiB	0.50 GiB	3.20×
16,384	0.31 GiB	1.00 GiB	3.20×
32,768	0.63 GiB	2.00 GiB	3.20×
65,536	1.25 GiB	4.00 GiB	3.20×
131,072	2.50 GiB	8.00 GiB	3.20×