Model comparison

orpheus-3b-0.1-ft vs Qwen3-TTS-12Hz-0.6B-Base

At Q4_K_M, orpheus-3b-0.1-ft is the smaller download — 2,092,567,712 bytes against 5,073,265,248.

From the file· summed bytes, KV per layer

Side by side

orpheus-3b-0.1-ftQwen3-TTS-12Hz-0.6B-Base
Parameters3.8B915M
Architecturellamaqwen3-tts
Layers28
Native context131,072
Mixture of expertsnono
Quantizations published2210
Smallest quantization0.91 GiB0.50 GiB
Q4_K_M1.95 GiB4.72 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
Contextorpheus-3b-0.1-ftQwen3-TTS-12Hz-0.6B-BaseRatio
4,0960.44 GiB
8,1920.88 GiB
16,3841.75 GiB
32,7683.50 GiB
65,5367.00 GiB
131,07214.00 GiB