MLX Community · First MLX build 19 May 2025
OuteTTS-1.0-0.6B
MLX
Audio apache-2.0
A 602M parameter text to speech model, with 5 MLX builds, from 3-bit to fp16.
- Parameters
- 602M From Hugging Face
- Quantisation
- fp16 OuteTTS-1.0-0.6B-fp16
- Memory needed
- 4 GB Estimate, unified memory
- Download
- 1.2 GB Weights, estimated
- Downloads
- 56 This build, last 30 days
- Task
- Text to speech Audio
- MLX builds
- 5 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 4 GB at fp16
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/OuteTTS-1.0-0.6B-fp16MLX builds
5 on mlx-community| OuteTTS-1.0-0.6B-3bit | 3-bit | 263 MB | 3 GB | 12 |
|---|---|---|---|---|
| OuteTTS-1.0-0.6B-4bit | 4-bit | 339 MB | 3 GB | 24 |
| OuteTTS-1.0-0.6B-6bit | 6-bit | 489 MB | 3 GB | 10 |
| OuteTTS-1.0-0.6B-8bit | 8-bit | 640 MB | 3 GB | 27 |
| OuteTTS-1.0-0.6B-fp16 | fp16 | 1.2 GB | 4 GB | 56 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.