Model comparison
VieNeu-TTS-0.3B vs chatterbox
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-0.3B | chatterbox | |
|---|---|---|
| Parameters | 244M | 264M |
| Architecture | qwen3 | chatterbox-s3gen |
| Layers | 28 | — |
| Native context | 4,096 | — |
| Mixture of experts | no | no |
| Quantizations published | 2 | 37 |
| Smallest quantization | 0.19 GiB | 0.17 GiB |
| Q4_K_M | — | 0.46 GiB |
| Licence | cc-by-nc-4.0 | mit |
KV cache by context
the term that decides long-context viability
| Context | VieNeu-TTS-0.3B | chatterbox | Ratio |
|---|---|---|---|
| 4,096 | 0.11 GiB | — | — |
| 8,192 | 0.22 GiB | — | — |
| 16,384 | 0.44 GiB | — | — |
| 32,768 | 0.88 GiB | — | — |
| 65,536 | 1.75 GiB | — | — |
| 131,072 | 3.50 GiB | — | — |