Skip to content

MOSS-TTS-Local-Transformer-v1.5-4bit

mlx-community/MOSS-TTS-Local-Transformer-v1.5-4bit
4-bit Open on Hugging Face
Parameters
4.6B
Weights (est.)
≈ 2.6 GB
Mac memory (est.)
8 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
OpenMOSS-Team/MOSS-TTS-Local-Transformer-v1.5 (quantized)
Vendor
OpenMOSS-Team
Task
Text to speech
Quantisation
4-bit
Licence
apache-2.0
Downloads
336 in the last 30 days · 693 all time · 0 likes
Published
2026-09-02 · updated 2026-09-02 (2mo ago)
Languages
zh, en, ja, ko, de, fr, es, it, ru, pt
Tags
moss_tts_local, mlx-audio, voice-cloning, streaming, apple-silicon, quantized, 4bit, custom_code

Other MLX builds of OpenMOSS-Team/MOSS-TTS-Local-Transformer-v1.5

Build Quantisation Weights Mac memory Downloads
MOSS-TTS-Local-Transformer-v1.5-4bit (this one) 4-bit ≈ 2.6 GB 8 GB+ 336
MOSS-TTS-Local-Transformer-v1.5-8bit 8-bit ≈ 4.9 GB 8 GB+ 480
MOSS-TTS-Local-Transformer-v1.5-bf16 bf16 ≈ 9.1 GB 16 GB+ 120