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

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

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

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

KV cache by context

the term that decides long-context viability

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