Is Qwen3.5-9B-GLM5.1-Distill-v1 or Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP smaller?

Qwen3.5-9B-GLM5.1-Distill-v1 is smaller at Q4_K_M: 5.24 GiB against 34.04 GiB.

Which uses less memory at long context?

Qwen3.5-9B-GLM5.1-Distill-v1 — its KV cache at 32K context is 2.0x smaller, because of how its attention layers cache.

Model comparison

Qwen3.5-9B-GLM5.1-Distill-v1 vs Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP

At Q4_K_M, Qwen3.5-9B-GLM5.1-Distill-v1 is the smaller download — 5,629,105,408 bytes against 36,545,830,912. At long context the gap widens: Qwen3.5-9B-GLM5.1-Distill-v1's KV cache at 32K is 2.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.5-9B-GLM5.1-Distill-v1	Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP
Parameters	9.7B	27.8B
Architecture	qwen35	qwen35
Layers	32	64
Native context	262,144	262,144
Mixture of experts	no	no
Quantizations published	9	34
Smallest quantization	4.31 GiB	10.12 GiB
Q4_K_M	5.24 GiB	34.04 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.5-9B-GLM5.1-Distill-v1	Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP	Ratio
4,096	0.13 GiB	0.25 GiB	2.00×
8,192	0.25 GiB	0.50 GiB	2.00×
16,384	0.50 GiB	1.00 GiB	2.00×
32,768	1.00 GiB	2.00 GiB	2.00×
65,536	2.00 GiB	4.00 GiB	2.00×
131,072	4.00 GiB	8.00 GiB	2.00×