Is MiMo-VL-7B-RL or Qwen3.5-9B smaller?

MiMo-VL-7B-RL is smaller at Q4_K_M: 4.36 GiB against 5.24 GiB.

Which uses less memory at long context?

Qwen3.5-9B — its KV cache at 32K context is 4.5x smaller, because of how its attention layers cache.

Model comparison

MiMo-VL-7B-RL vs Qwen3.5-9B

At Q4_K_M, MiMo-VL-7B-RL is the smaller download — 4,684,339,136 bytes against 5,627,044,256. At long context the gap widens: Qwen3.5-9B's KV cache at 32K is 4.5× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	MiMo-VL-7B-RL	Qwen3.5-9B
Parameters	8.3B	9.7B
Architecture	qwen2vl	qwen35
Layers	36	32
Native context	128,000	262,144
Mixture of experts	no	no
Quantizations published	64	34
Smallest quantization	1.86 GiB	2.97 GiB
Q4_K_M	4.36 GiB	5.24 GiB
Licence	mit	apache-2.0

KV cache by context

the term that decides long-context viability

Context	MiMo-VL-7B-RL	Qwen3.5-9B	Ratio
4,096	0.56 GiB	0.13 GiB	4.50×
8,192	1.13 GiB	0.25 GiB	4.50×
16,384	2.25 GiB	0.50 GiB	4.50×
32,768	4.50 GiB	1.00 GiB	4.50×
65,536	9.00 GiB	2.00 GiB	4.50×
131,072	18.00 GiB	4.00 GiB	4.50×