Is Qwen3.6-35B-A3B or Muse-Glimmer-30B smaller?

Muse-Glimmer-30B is smaller at Q4_K_M: 16.12 GiB against 19.71 GiB.

Which uses less memory at long context?

Muse-Glimmer-30B — its KV cache at 32K context is 1.2x smaller, because of how its attention layers cache.

Model comparison

Qwen3.6-35B-A3B vs Muse-Glimmer-30B

At Q4_K_M, Muse-Glimmer-30B is the smaller download — 17,306,324,000 bytes against 21,166,757,728. At long context the gap widens: Muse-Glimmer-30B'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

	Qwen3.6-35B-A3B	Muse-Glimmer-30B
Parameters	36.0B	29.8B
Architecture	qwen35moe	muse-glimmer
Layers	40	52
Native context	262,144	131,072
Mixture of experts	yes, 256 experts	no
Quantizations published	61	36
Smallest quantization	8.77 GiB	8.31 GiB
Q4_K_M	19.71 GiB	16.12 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.6-35B-A3B	Muse-Glimmer-30B	Ratio
4,096	0.08 GiB	0.15 GiB	1.87×
8,192	0.16 GiB	0.20 GiB	1.26×
16,384	0.31 GiB	0.30 GiB	1.05×
32,768	0.63 GiB	0.50 GiB	1.25×
65,536	1.25 GiB	0.91 GiB	1.38×
131,072	2.50 GiB	1.72 GiB	1.45×