Model comparison
Kokoro-82M vs VieNeu-TTS-0.3B
These two publish different quantization sets; the table below has the exact sizes.
From the file· summed bytes, KV per layer
Side by side
| Kokoro-82M | VieNeu-TTS-0.3B | |
|---|---|---|
| Parameters | 82M | 244M |
| Architecture | kokoro | qwen3 |
| Layers | 3 | 28 |
| Native context | — | 4,096 |
| Mixture of experts | no | no |
| Quantizations published | 4 | 2 |
| Smallest quantization | 0.13 GiB | 0.19 GiB |
| Q4_K_M | — | — |
| Licence | apache-2.0 | cc-by-nc-4.0 |
KV cache by context
the term that decides long-context viability
| Context | Kokoro-82M | VieNeu-TTS-0.3B | 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 | — |