OpenMOSS-Team · First MLX build 2 Sept 2026
MOSS-TTS-Local-Transformer-v1.5
MLX
Audio apache-2.0
A 4.6B parameter text to speech model from OpenMOSS-Team, with 3 MLX builds, from 4-bit to bf16.
- Parameters
- 4.6B From Hugging Face
- Quantisation
- 8-bit MOSS-TTS-Local-Transformer-v1.5-8bit
- Memory needed
- 8 GB Estimate, unified memory
- Download
- 4.9 GB Weights, estimated
- Downloads
- 493 This build, last 30 days
- Task
- Text to speech Audio
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 8 GB at 8-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/MOSS-TTS-Local-Transformer-v1.5-8bitMLX builds
3 on mlx-community| MOSS-TTS-Local-Transformer-v1.5-4bit | 4-bit | 2.6 GB | 5 GB | 343 |
|---|---|---|---|---|
| MOSS-TTS-Local-Transformer-v1.5-8bit | 8-bit | 4.9 GB | 8 GB | 493 |
| MOSS-TTS-Local-Transformer-v1.5-bf16 | bf16 | 9.1 GB | 13 GB | 122 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.