ekwek · First MLX build 3 Feb 2026
Soprano-1.1-80M
MLX
Audio
A 110M parameter text to speech model from ekwek, with 4 MLX builds, from 5-bit to bf16.
- Parameters
- 110M From Hugging Face
- Quantisation
- bf16 Soprano-1.1-80M-bf16
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 281 MB Weights, estimated
- Downloads
- 1.2K This build, last 30 days
- Task
- Text to speech Audio
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 3 GB at bf16
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/Soprano-1.1-80M-bf16MLX builds
4 on mlx-community| Soprano-1.1-80M-5bit | 5-bit | 77 MB | 3 GB | 62 |
|---|---|---|---|---|
| Soprano-1.1-80M-6bit | 6-bit | 91 MB | 3 GB | 24 |
| Soprano-1.1-80M-8bit | 8-bit | 118 MB | 3 GB | 76 |
| Soprano-1.1-80M-bf16 | bf16 | 281 MB | 3 GB | 1.2K |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.