Is Qwen3-VL-Embedding-2B or LFM2.5-VL-1.6B smaller?

LFM2.5-VL-1.6B is smaller at Q4_K_M: 0.68 GiB against 1.03 GiB.

Which uses less memory at long context?

LFM2.5-VL-1.6B — its KV cache at 32K context is 9.3x smaller, because of how its attention layers cache.

Model comparison

Qwen3-VL-Embedding-2B vs LFM2.5-VL-1.6B

At Q4_K_M, LFM2.5-VL-1.6B is the smaller download — 730,895,968 bytes against 1,107,410,528. At long context the gap widens: LFM2.5-VL-1.6B's KV cache at 32K is 9.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3-VL-Embedding-2B	LFM2.5-VL-1.6B
Parameters	2.1B	1.6B
Architecture	qwen3vl	lfm2
Layers	28	16
Native context	262,144	128,000
Mixture of experts	no	no
Quantizations published	11	23
Smallest quantization	0.72 GiB	0.45 GiB
Q4_K_M	1.03 GiB	0.68 GiB
Licence	—	other

KV cache by context

the term that decides long-context viability

Context	Qwen3-VL-Embedding-2B	LFM2.5-VL-1.6B	Ratio
4,096	0.44 GiB	0.05 GiB	9.33×
8,192	0.88 GiB	0.09 GiB	9.33×
16,384	1.75 GiB	0.19 GiB	9.33×
32,768	3.50 GiB	0.38 GiB	9.33×
65,536	7.00 GiB	0.75 GiB	9.33×
131,072	14.00 GiB	1.50 GiB	9.33×