Model comparison

ACE-Step-v1-3.5B vs embeddinggemma-300m

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

From the file· summed bytes, KV per layer

Side by side

ACE-Step-v1-3.5Bembeddinggemma-300m
Parameters3.3B303M
Architecturepiggemma-embedding
Layers24
Native context2,048
Mixture of expertsnono
Quantizations published1910
Smallest quantization0.42 GiB0.26 GiB
Q4_K_M5.73 GiB
Licenceapache-2.0

KV cache by context

the term that decides long-context viability
ContextACE-Step-v1-3.5Bembeddinggemma-300mRatio
4,0960.04 GiB
8,1920.05 GiB
16,3840.08 GiB
32,7680.14 GiB
65,5360.27 GiB
131,0720.52 GiB