6-bit Open on Hugging Face
Parameters
110M
Weights (est.)
≈ 91 MB
Mac memory (est.)
8 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Details
- Base model
- ekwek/Soprano-1.1-80M (quantized)
- Vendor
- ekwek
- Task
- Text to speech
- Quantisation
- 6-bit
- Licence
- —
- Downloads
- 23 in the last 30 days · 86 all time · 0 likes
- Published
- 2026-02-04 · updated 2026-02-04 (9mo ago)
- Tags
- mlx-audio, soprano, speech, speech generation, voice cloning
Other MLX builds of ekwek/Soprano-1.1-80M
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Soprano-1.1-80M-5bit | 5-bit | ≈ 77 MB | 8 GB+ | 59 |
| Soprano-1.1-80M-6bit (this one) | 6-bit | ≈ 91 MB | 8 GB+ | 23 |
| Soprano-1.1-80M-8bit | 8-bit | ≈ 118 MB | 8 GB+ | 73 |
| Soprano-1.1-80M-bf16 | bf16 | ≈ 281 MB | 8 GB+ | 1.2K |