Is Qwen3.6-27B or GLM-4.7-Flash-REAP-23B-A3B smaller?

GLM-4.7-Flash-REAP-23B-A3B is smaller at Q4_K_M: 13.14 GiB against 15.41 GiB.

Which uses less memory at long context?

GLM-4.7-Flash-REAP-23B-A3B — its KV cache at 32K context is 1.2x smaller, because of how its attention layers cache.

Model comparison

Qwen3.6-27B vs GLM-4.7-Flash-REAP-23B-A3B

At Q4_K_M, GLM-4.7-Flash-REAP-23B-A3B is the smaller download — 14,113,838,816 bytes against 16,547,397,888. At long context the gap widens: GLM-4.7-Flash-REAP-23B-A3B's KV cache at 32K is 1.2× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.6-27B	GLM-4.7-Flash-REAP-23B-A3B
Parameters	27.8B	23.0B
Architecture	qwen35	deepseek2
Layers	64	47
Native context	262,144	202,752
Mixture of experts	no	yes, 48 experts
Quantizations published	40	21
Smallest quantization	8.74 GiB	6.09 GiB
Q4_K_M	15.41 GiB	13.14 GiB
Licence	apache-2.0	mit

KV cache by context

the term that decides long-context viability

Context	Qwen3.6-27B	GLM-4.7-Flash-REAP-23B-A3B	Ratio
4,096	0.25 GiB	0.21 GiB	1.21×
8,192	0.50 GiB	0.41 GiB	1.21×
16,384	1.00 GiB	0.83 GiB	1.21×
32,768	2.00 GiB	1.65 GiB	1.21×
65,536	4.00 GiB	3.30 GiB	1.21×
131,072	8.00 GiB	6.61 GiB	1.21×