Microsoft · First MLX build 11 Jul 2025
MediPhi-Instruct
MLX
Text mit
A 3.8B parameter text generation model from Microsoft, with one MLX build at bf16.
- Parameters
- 3.8B From Hugging Face
- Quantisation
- bf16 MediPhi-Instruct-bf16
- Memory needed
- 11 GB Estimate, unified memory
- Download
- 7.6 GB Weights, estimated
- Downloads
- 32 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 11 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 · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/MediPhi-Instruct-bf16 --prompt "Hello"MLX builds
1 on mlx-community| MediPhi-Instruct-bf16 | bf16 | 7.6 GB | 11 GB | 32 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.