Model comparison
chatterbox vs VieNeu-TTS
These two publish different quantization sets; the table below has the exact sizes.
From the file· summed bytes, KV per layer
Side by side
| chatterbox | VieNeu-TTS | |
|---|---|---|
| Parameters | 264M | 553M |
| Architecture | chatterbox-s3gen | qwen2 |
| Layers | — | 24 |
| Native context | — | 32,768 |
| Mixture of experts | no | no |
| Quantizations published | 37 | 1 |
| Smallest quantization | 0.17 GiB | 0.39 GiB |
| Q4_K_M | 0.46 GiB | — |
| Licence | mit | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | chatterbox | VieNeu-TTS | 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 | — |