Aratako · First MLX build 4 Oct 2026
Irodori-TTS-v4-Large
MLX
Audio
A 3.3B parameter text to speech model from Aratako, with 2 MLX builds, from 8-bit to bf16.
- Parameters
- 3.3B From Hugging Face
- Quantisation
- bf16 Irodori-TTS-v4-Large-bf16
- Memory needed
- 10 GB Estimate, unified memory
- Download
- 6.6 GB Weights, estimated
- Downloads
- 104 This build, last 30 days
- Task
- Text to speech Audio
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 10 GB at bf16
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/Irodori-TTS-v4-Large-bf16MLX builds
2 on mlx-community| Irodori-TTS-v4-Large-8bit | 8-bit | 4.0 GB | 7 GB | 85 |
|---|---|---|---|---|
| Irodori-TTS-v4-Large-bf16 | bf16 | 6.6 GB | 10 GB | 104 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.