IndexTeam · First MLX build 9 Jul 2026
IndexTTS-2
MLX
Audio other
A 580M parameter text to speech model from IndexTeam, with 2 MLX builds at fp16.
- Parameters
- 580M From Hugging Face
- Quantisation
- Unstated IndexTTS-2-MLX
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 577 This build, last 30 days
- Task
- Text to speech Audio
- MLX builds
- 2 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/IndexTTS-2-MLXMLX builds
2 on mlx-community| IndexTTS-2-fp16 | fp16 | 2.3 GB | 5 GB | 284 |
|---|---|---|---|---|
| IndexTTS-2-MLX | Unstated | — | — | 577 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.