Is Qwen3.5-99B or Qwen-AgentWorld-35B-A3B smaller?

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

Which uses less memory at long context?

Qwen-AgentWorld-35B-A3B — its KV cache at 32K context is 1.2x smaller, because of how its attention layers cache.

Model comparison

Qwen3.5-99B vs Qwen-AgentWorld-35B-A3B

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

	Qwen3.5-99B	Qwen-AgentWorld-35B-A3B
Parameters	99.0B	34.7B
Architecture	qwen35moe	qwen35moe
Layers	48	40
Native context	262,144	262,144
Mixture of experts	yes, 205 experts	yes, 256 experts
Quantizations published	36	15
Smallest quantization	19.31 GiB	10.71 GiB
Q4_K_M	56.06 GiB	—
Licence	other	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.5-99B	Qwen-AgentWorld-35B-A3B	Ratio
4,096	0.09 GiB	0.08 GiB	1.20×
8,192	0.19 GiB	0.16 GiB	1.20×
16,384	0.38 GiB	0.31 GiB	1.20×
32,768	0.75 GiB	0.63 GiB	1.20×
65,536	1.50 GiB	1.25 GiB	1.20×
131,072	3.00 GiB	2.50 GiB	1.20×