Model comparison

VoxCPM2 vs orpheus-3b-0.1-ft

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

From the file· summed bytes, KV per layer

Side by side

VoxCPM2orpheus-3b-0.1-ft
Parameters2.3B3.8B
Architecturevoxcpm-acousticllama
Layers28
Native context131,072
Mixture of expertsnono
Quantizations published722
Smallest quantization1.57 GiB0.91 GiB
Q4_K_M1.95 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextVoxCPM2orpheus-3b-0.1-ftRatio
4,0960.44 GiB
8,1920.88 GiB
16,3841.75 GiB
32,7683.50 GiB
65,5367.00 GiB
131,07214.00 GiB