Is MiMo-VL-7B-RL or Qwythos-9B-v2 smaller?

MiMo-VL-7B-RL is smaller at Q4_K_M: 4.36 GiB against 5.63 GiB.

Which uses less memory at long context?

Qwythos-9B-v2 — its KV cache at 32K context is 4.5x smaller, because of how its attention layers cache.

Model comparison

MiMo-VL-7B-RL vs Qwythos-9B-v2

At Q4_K_M, MiMo-VL-7B-RL is the smaller download — 4,684,339,136 bytes against 6,047,707,680. At long context the gap widens: Qwythos-9B-v2'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	Qwythos-9B-v2
Parameters	8.3B	9.7B
Architecture	qwen2vl	qwen35
Layers	36	32
Native context	128,000	1,048,576
Mixture of experts	no	no
Quantizations published	64	43
Smallest quantization	1.86 GiB	3.64 GiB
Q4_K_M	4.36 GiB	5.63 GiB
Licence	mit	apache-2.0

KV cache by context

the term that decides long-context viability

Context	MiMo-VL-7B-RL	Qwythos-9B-v2	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×