Model comparison

ACE-Step-v1-3.5B vs gemma-3-1b-it

At Q4_K_M, gemma-3-1b-it is the smaller download — 806,058,240 bytes against 6,149,775,712.

From the file· summed bytes, KV per layer

Side by side

ACE-Step-v1-3.5Bgemma-3-1b-it
Parameters3.3B1000M
Architecturepiggemma3
Layers26
Native context32,768
Mixture of expertsnono
Quantizations published1928
Smallest quantization0.42 GiB0.52 GiB
Q4_K_M5.73 GiB0.75 GiB
Licenceapache-2.0gemma

KV cache by context

the term that decides long-context viability
ContextACE-Step-v1-3.5Bgemma-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