Skip to content

MiLMMT-46-12B-v0.1-6bit

mlx-community/MiLMMT-46-12B-v0.1-6bit
6-bit Open on Hugging Face
Parameters
13B
Weights (est.)
≈ 10.4 GB
Mac memory (est.)
16 GB+

Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.

Details

Base model
xiaomi-research/MiLMMT-46-12B-v0.1 (quantized)
Vendor
xiaomi-research
Task
Translation
Quantisation
6-bit
Licence
gemma
Downloads
39 in the last 30 days · 310 all time · 1 likes
Published
2026-07-22 · updated 2026-07-22 (3mo ago)
Tags
gemma3

Other MLX builds of xiaomi-research/MiLMMT-46-12B-v0.1

Build Quantisation Weights Mac memory Downloads
MiLMMT-46-12B-v0.1-4bit 4-bit ≈ 7.2 GB 16 GB+ 34
MiLMMT-46-12B-v0.1-6bit (this one) 6-bit ≈ 10.4 GB 16 GB+ 39