Model comparison
VieNeu-TTS vs OmniVoice
These two publish different quantization sets; the table below has the exact sizes.
From the file· summed bytes, KV per layer
Side by side
| VieNeu-TTS | OmniVoice | |
|---|---|---|
| Parameters | 553M | 613M |
| Architecture | qwen2 | omnivoice-lm |
| Layers | 24 | — |
| Native context | 32,768 | — |
| Mixture of experts | no | no |
| Quantizations published | 1 | 7 |
| Smallest quantization | 0.39 GiB | 0.56 GiB |
| Q4_K_M | — | 0.61 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | VieNeu-TTS | OmniVoice | Ratio |
|---|---|---|---|
| 4,096 | 0.05 GiB | — | — |
| 8,192 | 0.09 GiB | — | — |
| 16,384 | 0.19 GiB | — | — |
| 32,768 | 0.38 GiB | — | — |
| 65,536 | 0.75 GiB | — | — |
| 131,072 | 1.50 GiB | — | — |