Is Qwen3.5-9B-DFlash or KaLM-embedding-multilingual-mini-instruct-v2.5 smaller?

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

Which uses less memory at long context?

Qwen3.5-9B-DFlash — its KV cache at 32K context is 1.8x smaller, because of how its attention layers cache.

Model comparison

Qwen3.5-9B-DFlash vs KaLM-embedding-multilingual-mini-instruct-v2.5

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: Qwen3.5-9B-DFlash's KV cache at 32K is 1.8× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.5-9B-DFlash	KaLM-embedding-multilingual-mini-instruct-v2.5
Parameters	1.3B	494M
Architecture	dflash	qwen2
Layers	6	24
Native context	262,144	131,072
Mixture of experts	no	no
Quantizations published	11	1
Smallest quantization	0.45 GiB	0.49 GiB
Q4_K_M	0.71 GiB	—
Licence	—	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.5-9B-DFlash	KaLM-embedding-multilingual-mini-instruct-v2.5	Ratio
4,096	0.09 GiB	0.05 GiB	2.00×
8,192	0.12 GiB	0.09 GiB	1.27×
16,384	0.15 GiB	0.19 GiB	1.25×
32,768	0.21 GiB	0.38 GiB	1.76×
65,536	0.34 GiB	0.75 GiB	2.22×
131,072	0.59 GiB	1.50 GiB	2.55×