Model comparison

orpheus-3b-0.1-ft vs OmniVoice

At Q4_K_M, OmniVoice is the smaller download — 659,959,328 bytes against 2,092,567,712.

From the file· summed bytes, KV per layer

Side by side

orpheus-3b-0.1-ftOmniVoice
Parameters3.8B613M
Architecturellamaomnivoice-lm
Layers28
Native context131,072
Mixture of expertsnono
Quantizations published227
Smallest quantization0.91 GiB0.56 GiB
Q4_K_M1.95 GiB0.61 GiB
Licenceapache-2.0apache-2.0

KV cache by context

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