Downloads · 30 days
3
9% of all-time downloads
milmmt-46-4b-mlx-4bit
shraey/milmmt-46-4b-mlx-4bit
milmmt-46-4b-mlx-4bit is a machine learning model from shraey. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
MLX 4-bit weights for the MiLMMT translation model, for Apple-silicon (MLX) inference (via mlxlm).
All-time downloads
32
Public
Parameters
711M
2.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.6 GB · 99%
Parameter types
How the weights are stored.
U32569M · 80%
Model card
From the Hugging Face model README
MiLMMT-4.6B — MLX (4-bit, translation)
MLX 4-bit weights for the MiLMMT translation model, for Apple-silicon (MLX) inference (via mlx_lm).
Attribution & license
- Upstream: xiaomi-research/MiLMMT-46-4B-v0.1 (Xiaomi MiLM Plus + Xiamen University), built on Google Gemma 3.
- License: Gemma Terms of Use — commercial use + redistribution permitted, subject to Google's Gemma Prohibited Use Policy. This MLX 4-bit derivative is distributed under the same Gemma terms; downstream users are bound by them.
- Type
- gemma3
- Created
- Jun 23, 2026
- Updated
- Jun 23, 2026