MLX Community · First MLX build 18 Dec 2025
VyvoTTS-EN-Beta
MLX
Text Gated
A 1.8B parameter text generation model, with 5 MLX builds, from 4-bit to fp16.
- Parameters
- 1.8B From Hugging Face
- Quantisation
- 4-bit VyvoTTS-EN-Beta-4bit
- Memory needed
- 4 GB Estimate, unified memory
- Download
- 1.0 GB Weights, estimated
- Downloads
- 84 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 5 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 4 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/VyvoTTS-EN-Beta-4bitMLX builds
5 on mlx-community| VyvoTTS-EN-Beta-4bit | 4-bit | 1.0 GB | 4 GB | 84 |
|---|---|---|---|---|
| VyvoTTS-EN-Beta-5bit Gated | 5-bit | 1.2 GB | 4 GB | 2 |
| VyvoTTS-EN-Beta-6bit Gated | 6-bit | 1.4 GB | 4 GB | 2 |
| VyvoTTS-EN-Beta-8bit Gated | 8-bit | 1.9 GB | 5 GB | 2 |
| VyvoTTS-EN-Beta-fp16 Gated | fp16 | 3.6 GB | 6 GB | 2 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.