Is Qwen3.8-27B or Qwen3.6-35B-REAP-Pruned-ratio-0.5 smaller?

Qwen3.6-35B-REAP-Pruned-ratio-0.5 is smaller at Q4_K_M: 10.59 GiB against 15.66 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

Qwen3.8-27B vs Qwen3.6-35B-REAP-Pruned-ratio-0.5

At Q4_K_M, Qwen3.6-35B-REAP-Pruned-ratio-0.5 is the smaller download — 11,373,050,592 bytes against 16,810,714,336. 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

	Qwen3.8-27B	Qwen3.6-35B-REAP-Pruned-ratio-0.5
Parameters	27.8B	19.0B
Architecture	qwen35	qwen35moe
Layers	64	40
Native context	262,144	262,144
Mixture of experts	no	yes, 128 experts
Quantizations published	22	2
Smallest quantization	8.39 GiB	10.59 GiB
Q4_K_M	15.66 GiB	10.59 GiB
Licence	apache-2.0	—

KV cache by context

the term that decides long-context viability

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