xiaomi-research · First MLX build 21 Jul 2026
MiLMMT-46-12B-v0.1
MLX
Text gemma
A 13B parameter translation model from xiaomi-research, with 2 MLX builds, from 4-bit to 6-bit.
- Parameters
- 13B From Hugging Face
- Quantisation
- 6-bit MiLMMT-46-12B-v0.1-6bit
- Memory needed
- 14 GB Estimate, unified memory
- Download
- 10.4 GB Weights, estimated
- Downloads
- 39 This build, last 30 days
- Task
- Translation Text
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 14 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-46-12B-v0.1-6bitMLX builds
2 on mlx-community| MiLMMT-46-12B-v0.1-4bit | 4-bit | 7.2 GB | 11 GB | 34 |
|---|---|---|---|---|
| MiLMMT-46-12B-v0.1-6bit | 6-bit | 10.4 GB | 14 GB | 39 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.