MOSS-TTS-Local-Transformer-v1.5 โ€” MLX int8

8-bit (int8) MLX quantization of OpenMOSS-Team/MOSS-TTS-Local-Transformer-v1.5 โ€” a multilingual, 48 kHz, on-device text-to-speech model โ€” for Apple Silicon via mlx-audio.

This repo only re-hosts an int8-quantized copy of OpenMOSS's weights. All model design, training, and capabilities are OpenMOSS's work โ€” see their card for the full details.

Base model OpenMOSS-Team/MOSS-TTS-Local-Transformer-v1.5 (Qwen3-4B backbone + local transformer)
License Apache-2.0 (inherited from the base model)
Quantization int8, group_size 64, affine (mlx-audio converter)
Size ~4.55 GB (vs ~9.1 GB bf16)
Codec pairs with shraey/MOSS-Audio-Tokenizer-v2-MLX-int8 (~2.23 GB) โ€” auto-resolved by this model's config

Use

from mlx_audio.tts import load
model = load("shraey/MOSS-TTS-Local-Transformer-v1.5-MLX-int8", lazy=True)
result = next(model.generate(text="Hello, running on device.", language="English", max_tokens=200))

Capabilities (from the base model): 31 languages + code-switching, 48 kHz stereo, transcript-optional zero-shot cloning (ref_audio), highest-fidelity "continuation" cloning (mode="continuation" + ref_text), inline [pause X.Ys], and native single-call long-form. Always pass language= when known.

Requires mlx-audio with the codec-quant-load patch so the paired int8 codec loads โ€” mlx-audio @ git+https://github.com/sb1992/mlx-audio@9154d5a (a PR to upstream Blaizzy/mlx-audio is pending). Total download with the int8 codec โ‰ˆ 6.8 GB.

Downloads last month
92
Safetensors
Model size
5B params
Tensor type
BF16
ยท
U32
ยท
MLX
Hardware compatibility
Log In to add your hardware

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for shraey/MOSS-TTS-Local-Transformer-v1.5-MLX-int8

Quantized
(8)
this model