MLX Community · First MLX build 22 Apr 2025
Llama-OuteTTS-1.0-1B
MLX
Audio cc-by-nc-sa-4.0
A 1.2B parameter text to speech model, with 5 MLX builds, from 3-bit to fp16.
- Parameters
- 1.2B From Hugging Face
- Quantisation
- 4-bit Llama-OuteTTS-1.0-1B-4bit
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 702 MB Weights, estimated
- Downloads
- 1.2K 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 3 GB at 4-bit
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/Llama-OuteTTS-1.0-1B-4bitMLX builds
5 on mlx-community| Llama-OuteTTS-1.0-1B-3bit | 3-bit | 546 MB | 3 GB | 17 |
|---|---|---|---|---|
| Llama-OuteTTS-1.0-1B-4bit | 4-bit | 702 MB | 3 GB | 1.2K |
| Llama-OuteTTS-1.0-1B-6bit | 6-bit | 1.0 GB | 4 GB | 19 |
| Llama-OuteTTS-1.0-1B-8bit | 8-bit | 1.3 GB | 4 GB | 33 |
| Llama-OuteTTS-1.0-1B-fp16 | fp16 | 2.5 GB | 5 GB | 26 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.