huihui-ai · First MLX build 9 Jan 2025
phi-4-abliterated
MLX
Text mit
A 15B parameter text generation model from huihui-ai, with 5 MLX builds, from 2-bit to 8-bit.
- Parameters
- 15B From Hugging Face
- Quantisation
- 4-bit phi-4-abliterated-4bit
- Memory needed
- 12 GB Estimate, unified memory
- Download
- 8.2 GB Weights, estimated
- Downloads
- 106 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 12 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 · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/phi-4-abliterated-4bit --prompt "Hello"MLX builds
5 on mlx-community| phi-4-abliterated-2bit | 2-bit | 4.6 GB | 8 GB | 49 |
|---|---|---|---|---|
| phi-4-abliterated-3bit | 3-bit | 6.4 GB | 10 GB | 37 |
| phi-4-abliterated-4bit | 4-bit | 8.2 GB | 12 GB | 106 |
| phi-4-abliterated-6bit | 6-bit | 11.9 GB | 16 GB | 32 |
| phi-4-abliterated-8bit | 8-bit | 15.6 GB | 20 GB | 36 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.