Is Qwen3.5-9B-Star-Trek-TNG-DS9-Heretic-Uncensored-Thinking or Qwen3.6-35B-A3B smaller?

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

Which uses less memory at long context?

Qwen3.6-35B-A3B — its KV cache at 32K context is 1.6x smaller, because of how its attention layers cache.

Model comparison

Qwen3.5-9B-Star-Trek-TNG-DS9-Heretic-Uncensored-Thinking vs Qwen3.6-35B-A3B

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: Qwen3.6-35B-A3B's KV cache at 32K is 1.6× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.5-9B-Star-Trek-TNG-DS9-Heretic-Uncensored-Thinking	Qwen3.6-35B-A3B
Parameters	9.4B	36.0B
Architecture	qwen35	qwen35moe
Layers	32	40
Native context	262,144	262,144
Mixture of experts	no	yes, 256 experts
Quantizations published	2	61
Smallest quantization	9.77 GiB	8.77 GiB
Q4_K_M	—	19.71 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.5-9B-Star-Trek-TNG-DS9-Heretic-Uncensored-Thinking	Qwen3.6-35B-A3B	Ratio
4,096	0.13 GiB	0.08 GiB	1.60×
8,192	0.25 GiB	0.16 GiB	1.60×
16,384	0.50 GiB	0.31 GiB	1.60×
32,768	1.00 GiB	0.63 GiB	1.60×
65,536	2.00 GiB	1.25 GiB	1.60×
131,072	4.00 GiB	2.50 GiB	1.60×