MLX Community · First MLX build 30 Mar 2026
LongCat-AudioDiT-1B
MLX
Audio
A 1.4B parameter text to speech model, with 8 MLX builds, from 4-bit to bf16.
- Parameters
- 1.4B From Hugging Face
- Quantisation
- bf16 LongCat-AudioDiT-1B-bf16
- Memory needed
- 9 GB Estimate, unified memory
- Download
- 5.7 GB Weights, estimated
- Downloads
- 130 This build, last 30 days
- Task
- Text to speech Audio
- MLX builds
- 8 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 9 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/LongCat-AudioDiT-1B-bf16MLX builds
8 on mlx-community| LongCat-AudioDiT-1B-4bit | 4-bit | 1.3 GB | 4 GB | 31 |
|---|---|---|---|---|
| LongCat-AudioDiT-1B-mxfp4 | MXFP4 | 1.3 GB | 4 GB | 15 |
| LongCat-AudioDiT-1B-nvfp4 | 4-bit | 1.3 GB | 4 GB | 12 |
| LongCat-AudioDiT-1B-5bit | 5-bit | 1.5 GB | 4 GB | 9 |
| LongCat-AudioDiT-1B-6bit | 6-bit | 1.7 GB | 4 GB | 9 |
| LongCat-AudioDiT-1B-8bit | 8-bit | 2.0 GB | 5 GB | 55 |
| LongCat-AudioDiT-1B-mxfp8 | MXFP8 | 2.0 GB | 5 GB | 14 |
| LongCat-AudioDiT-1B-bf16 | bf16 | 5.7 GB | 9 GB | 130 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.