Model comparison

LFM2.5-Audio-1.5B vs gemma-3-1b-it

These two publish different quantization sets; the table below has the exact sizes.

From the file· summed bytes, KV per layer

Side by side

LFM2.5-Audio-1.5Bgemma-3-1b-it
Parameters1.5B1000M
Architecturelfm2gemma3
Layers26
Native context32,768
Mixture of expertsnono
Quantizations published628
Smallest quantization0.80 GiB0.52 GiB
Q4_K_M0.75 GiB
Licenceothergemma

KV cache by context

the term that decides long-context viability
ContextLFM2.5-Audio-1.5Bgemma-3-1b-itRatio
4,0960.04 GiB
8,1920.05 GiB
16,3840.08 GiB
32,7680.15 GiB
65,5360.27 GiB
131,0720.52 GiB