Skip to content

MuseTalk-1.5-q4

mlx-community/MuseTalk-1.5-q4
4-bit Open on Hugging Face
Parameters
—
Weights (est.)
—
Mac memory (est.)
—

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
TMElyralab/MuseTalk (finetune)
Vendor
TMElyralab
Task
Image to image
Quantisation
4-bit
Licence
mit
Downloads
1.1K in the last 30 days · 2.5K all time · 3 likes
Published
2026-06-05 · updated 2026-06-05 (5mo ago)
Tags
lip-sync, talking-head, musetalk, apple-silicon

Other MLX builds of TMElyralab/MuseTalk

Build Quantisation Weights Mac memory Downloads
face-parsing-bisenet-bf16 bf16 ≈ 27 MB 8 GB+ 55
MuseTalk-1.5-fp16 fp16 — — 1.3K
MuseTalk-1.5-q4 (this one) 4-bit — — 1.1K
MuseTalk-1.5-q8 8-bit — — 380