Model comparison

ACE-Step-v1-3.5B vs Qwen3-4B

At Q4_K_M, Qwen3-4B is the smaller download — 2,497,280,256 bytes against 6,149,775,712.

From the file· summed bytes, KV per layer

Side by side

ACE-Step-v1-3.5BQwen3-4B
Parameters3.3B4.0B
Architecturepigqwen3
Layers36
Native context40,960
Mixture of expertsnono
Quantizations published1929
Smallest quantization0.42 GiB1.01 GiB
Q4_K_M5.73 GiB2.33 GiB
Licenceapache-2.0

KV cache by context

the term that decides long-context viability
ContextACE-Step-v1-3.5BQwen3-4BRatio
4,0960.56 GiB
8,1921.13 GiB
16,3842.25 GiB
32,7684.50 GiB
65,5369.00 GiB
131,07218.00 GiB