Is Carnice-Qwen3.6-MoE-35B-A3B or Qwen3.6-27B smaller?

Both publish quantizations; compare the table for the exact sizes.

Which uses less memory at long context?

Carnice-Qwen3.6-MoE-35B-A3B — its KV cache at 32K context is 3.2x smaller, because of how its attention layers cache.

Model comparison

Carnice-Qwen3.6-MoE-35B-A3B vs Qwen3.6-27B

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: Carnice-Qwen3.6-MoE-35B-A3B'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

	Carnice-Qwen3.6-MoE-35B-A3B	Qwen3.6-27B
Parameters	36.0B	27.8B
Architecture	qwen35moe	qwen35
Layers	40	64
Native context	262,144	262,144
Mixture of experts	yes, 256 experts	no
Quantizations published	24	40
Smallest quantization	6.97 GiB	8.74 GiB
Q4_K_M	—	15.41 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Carnice-Qwen3.6-MoE-35B-A3B	Qwen3.6-27B	Ratio
4,096	0.08 GiB	0.25 GiB	3.20×
8,192	0.16 GiB	0.50 GiB	3.20×
16,384	0.31 GiB	1.00 GiB	3.20×
32,768	0.63 GiB	2.00 GiB	3.20×
65,536	1.25 GiB	4.00 GiB	3.20×
131,072	2.50 GiB	8.00 GiB	3.20×