Skip to content

SoulX-Singer-8bit

mlx-community/SoulX-Singer-8bit
8-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
Soul-AILab/SoulX-Singer (finetune)
Vendor
Soul-AILab
Task
Text to audio
Quantisation
8-bit
Licence
apache-2.0
Downloads
63 in the last 30 days · 444 all time · 0 likes
Published
2026-05-31 · updated 2026-05-31 (5mo ago)
Tags
apple-silicon, singing-voice-synthesis, singing-voice-conversion, soulx-singer

Other MLX builds of Soul-AILab/SoulX-Singer

Build Quantisation Weights Mac memory Downloads
SoulX-Singer-bf16 bf16 — — 216
SoulX-Singer — — — 155
SoulX-Singer-fp32 fp32 — — 133
SoulX-Singer-4bit 4-bit — — 110
SoulX-Singer-8bit (this one) 8-bit — — 63