Model comparison
OmniVoice vs Qwen3-TTS-12Hz-0.6B-Base
At Q4_K_M, OmniVoice is the smaller download — 659,959,328 bytes against 5,073,265,248.
From the file· summed bytes, KV per layer
Side by side
| OmniVoice | Qwen3-TTS-12Hz-0.6B-Base | |
|---|---|---|
| Parameters | 613M | 915M |
| Architecture | omnivoice-lm | qwen3-tts |
| Layers | — | — |
| Native context | — | — |
| Mixture of experts | no | no |
| Quantizations published | 7 | 10 |
| Smallest quantization | 0.56 GiB | 0.50 GiB |
| Q4_K_M | 0.61 GiB | 4.72 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | OmniVoice | Qwen3-TTS-12Hz-0.6B-Base | Ratio |
|---|---|---|---|
| 4,096 | — | — | — |
| 8,192 | — | — | — |
| 16,384 | — | — | — |
| 32,768 | — | — | — |
| 65,536 | — | — | — |
| 131,072 | — | — | — |