kenpath · First MLX build 26 Apr 2026
svara-tts-v1
MLX
Audio apache-2.0
A 3.3B parameter text to speech model from kenpath, with 3 MLX builds, from 4-bit to 8-bit.
- Parameters
- 3.3B From Hugging Face
- Quantisation
- 4-bit svara-tts-v1-4bit
- Memory needed
- 5 GB Estimate, unified memory
- Download
- 1.9 GB Weights, estimated
- Downloads
- 161 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 5 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/svara-tts-v1-4bitMLX builds
3 on mlx-community| svara-tts-v1-4bit | 4-bit | 1.9 GB | 5 GB | 161 |
|---|---|---|---|---|
| svara-tts-v1-8bit | 8-bit | 3.5 GB | 6 GB | 93 |
| svara-tts-v1 | Unstated | 6.6 GB | 10 GB | 30 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.