You can deploy this model and start earning money today!

owlninjam/
qwen3-tts-1.7b-customvoice-fp16

Name: qwen3-tts-1.7b-customvoice-fp16
Availability: InStock

Views

No views yet

qwen3-tts-1.7b-customvoice-fp16

GTX 1650 and other Turing GPUs don't support bfloat16 natively. Pre-converted fp16 weights load directly without runtime casting.

python

from qwen_tts import Qwen3TTSModel
model = Qwen3TTSModel.from_pretrained("owlninjam/qwen3-tts-1.7b-customvoice-fp16", dtype=torch.float16)