facebook · First MLX build 24 Dec 2025
PE-Core-G14-448
MLX
A 2.4B parameter model from facebook, with one MLX build.
- Parameters
- 2.4B From Hugging Face
- Quantisation
- Unstated PE-Core-G14-448
- Memory needed
- 13 GB Estimate, unified memory
- Download
- 9.7 GB Weights, estimated
- Downloads
- 21 This build, last 30 days
- Task
- —
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 13 GB at Unstated
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/PE-Core-G14-448MLX builds
1 on mlx-community| PE-Core-G14-448 | Unstated | 9.7 GB | 13 GB | 21 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.