inclusionAI · First MLX build 19 Oct 2026
Ming-3.0-tts-tiny
MLX
Audio mit
A 9B parameter text to speech model from inclusionAI, with 3 MLX builds, from 4-bit to bf16.
- Parameters
- 9B From Hugging Face
- Quantisation
- 8-bit Ming-3.0-tts-tiny-8bit
- Memory needed
- 14 GB Estimate, unified memory
- Download
- 10.6 GB Weights, estimated
- Downloads
- 532 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 14 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/Ming-3.0-tts-tiny-8bitMLX builds
3 on mlx-community| Ming-3.0-tts-tiny-4bit | 4-bit | 6.6 GB | 10 GB | 376 |
|---|---|---|---|---|
| Ming-3.0-tts-tiny-8bit | 8-bit | 10.6 GB | 14 GB | 532 |
| Ming-3.0-tts-tiny-bf16 | bf16 | 18.0 GB | 23 GB | 324 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.