Model comparison
VieNeu-TTS vs neutts-air
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 | neutts-air | |
|---|---|---|
| Parameters | 553M | 748M |
| Architecture | qwen2 | qwen2 |
| Layers | 24 | 24 |
| Native context | 32,768 | 32,768 |
| Mixture of experts | no | no |
| Quantizations published | 1 | 6 |
| Smallest quantization | 0.39 GiB | 0.43 GiB |
| Q4_K_M | — | 0.43 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | VieNeu-TTS | neutts-air | Ratio |
|---|---|---|---|
| 4,096 | 0.05 GiB | 0.05 GiB | 1.00× |
| 8,192 | 0.09 GiB | 0.09 GiB | 1.00× |
| 16,384 | 0.19 GiB | 0.19 GiB | 1.00× |
| 32,768 | 0.38 GiB | 0.38 GiB | 1.00× |
| 65,536 | 0.75 GiB | 0.75 GiB | 1.00× |
| 131,072 | 1.50 GiB | 1.50 GiB | 1.00× |