Model comparison

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

At Q4_K_M, LFM2.5-VL-1.6B is the smaller download — 730,895,968 bytes against 1,270,808,032.

From the file· summed bytes, KV per layer

Side by side

LFM2.5-VL-1.6BQwen3.5-2B
Parameters1.6B2.3B
Architecturelfm2qwen35
Layers1624
Native context128,000262,144
Mixture of expertsnono
Quantizations published2342
Smallest quantization0.45 GiB0.72 GiB
Q4_K_M0.68 GiB1.18 GiB
Licenceotherapache-2.0

KV cache by context

the term that decides long-context viability
ContextLFM2.5-VL-1.6BQwen3.5-2BRatio
4,0960.05 GiB0.05 GiB1.00×
8,1920.09 GiB0.09 GiB1.00×
16,3840.19 GiB0.19 GiB1.00×
32,7680.38 GiB0.38 GiB1.00×
65,5360.75 GiB0.75 GiB1.00×
131,0721.50 GiB1.50 GiB1.00×
LFM2.5-VL-1.6B vs Qwen3.5-2B — size, memory and hardware fit — ossmodeldb