xiaomi-research · First MLX build 22 Jul 2026
MiLMMT-46-4B-v0.1
MLX
Text gemma
A 4.6B parameter translation model from xiaomi-research, with one MLX build at 6-bit.
- Parameters
- 4.6B From Hugging Face
- Quantisation
- 6-bit MiLMMT-46-4B-v0.1-6bit
- Memory needed
- 7 GB Estimate, unified memory
- Download
- 3.7 GB Weights, estimated
- Downloads
- 15 This build, last 30 days
- Task
- Translation Text
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 7 GB at 6-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/MiLMMT-46-4B-v0.1-6bitMLX builds
1 on mlx-community| MiLMMT-46-4B-v0.1-6bit | 6-bit | 3.7 GB | 7 GB | 15 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.