groxaxo/MOSS-TTS-v1.5-Argentina-MLX-oQ5-HQ8Speech-G64

🤗 Hugging Face sourcetext-to-speechapache-2.08.5B params17 GBsafetensors✓ 321 checksumsupdated today

Submit in one command

Run it next to your model folder. It makes the torrent, checks your files against Hugging Face, and submits it. You just start seeding and paste your key from your account. It only reads your files and never changes them. Read the script first if you like.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo groxaxo/MOSS-TTS-v1.5-Argentina-MLX-oQ5-HQ8Speech-G64 ./model-folder

Needs a seeder →

MOSS-TTS v1.5 Argentina — MLX mixed-bit

MLX deployment build of a locally trained Argentine Spanish LoRA for OpenMOSS-Team/MOSS-TTS-v1.5. The selected adapter continued the selected female checkpoint for three epochs over the male Argentine split.

Quantization uses the recipe recovered from the owner's Mac:

normal Qwen3 backbone matrices: Q5 affine, group size 64
v_proj, down_proj, and transformer blocks 0–3 and 32–35: Q6 affine, group size 64
embeddings, LM/audio heads, and other speech-path modules: Q8 affine, group size 64
norms, biases, and the external audio tokenizer remain full precision

The LoRA was merged into luisarn/MOSS-TTS-v1.5-MLX-8bit before quantization. Adapter source label: MOSS-TTS-v1.5-Argentina-combined-female-epoch1-then-male-epoch2.

Load with a compatible mlx-audio checkout containing support for MOSS-TTS v1.5 and per-layer mixed quantization entries.