SicariusSicariiStuff · First MLX build 18 Jun 2025
Phi-lthy4
MLX
mit
A 12B parameter model from SicariusSicariiStuff, with one MLX build at 8-bit.
- Parameters
- 12B From Hugging Face
- Quantisation
- 8-bit Phi-lthy4-mlx-8Bit
- Memory needed
- 17 GB Estimate, unified memory
- Download
- 12.7 GB Weights, estimated
- Downloads
- 17 This build, last 30 days
- Task
- —
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 17 GB at 8-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/Phi-lthy4-mlx-8BitMLX builds
1 on mlx-community| Phi-lthy4-mlx-8Bit | 8-bit | 12.7 GB | 17 GB | 17 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.