Soul-AILab · First MLX build 31 May 2026
SoulX-Singer
MLX
Audio apache-2.0
A text to audio model from Soul-AILab, with 5 MLX builds, from bf16 to 8-bit.
- Parameters
- — Not published
- Quantisation
- bf16 SoulX-Singer-bf16
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 206 This build, last 30 days
- Task
- Text to audio Audio
- MLX builds
- 5 On mlx-community
- Devices
- Mac Apple silicon
Memory
Hugging Face does not list a weights size for this build, so there is no memory estimate.
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/SoulX-Singer-bf16MLX builds
5 on mlx-community| SoulX-Singer-bf16 | bf16 | — | — | 206 |
|---|---|---|---|---|
| SoulX-Singer | Unstated | — | — | 155 |
| SoulX-Singer-fp32 | fp32 | — | — | 131 |
| SoulX-Singer-4bit | 4-bit | — | — | 109 |
| SoulX-Singer-8bit | 8-bit | — | — | 64 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.