MLX Community · First MLX build 8 Jan 2026
LFM2.5-Audio-1.5B
MLX
Audio lfm1.0
A 1.5B parameter audio to audio model, with 5 MLX builds, from 4-bit to bf16.
- Parameters
- 1.5B From Hugging Face
- Quantisation
- 4-bit LFM2.5-Audio-1.5B-4bit
- Memory needed
- 4 GB Estimate, unified memory
- Download
- 1.1 GB Weights, estimated
- Downloads
- 299 This build, last 30 days
- Task
- Audio to audio Audio
- 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/LFM2.5-Audio-1.5B-4bitMLX builds
5 on mlx-community| LFM2.5-Audio-1.5B-4bit | 4-bit | 1.1 GB | 4 GB | 299 |
|---|---|---|---|---|
| LFM2.5-Audio-1.5B-5bit | 5-bit | 1.2 GB | 4 GB | 20 |
| LFM2.5-Audio-1.5B-6bit | 6-bit | 1.4 GB | 4 GB | 43 |
| LFM2.5-Audio-1.5B-8bit | 8-bit | 1.7 GB | 4 GB | 67 |
| LFM2.5-Audio-1.5B-bf16 | bf16 | 2.9 GB | 6 GB | 93 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.