Hugging Face's logo

divyajot5005
/
Qwen3-TTS-12Hz-1.7B-Base-BNB-4bit

Text-to-Speech
Transformers
Safetensors
Qwen3-TTS
text-generation
tts
qwen3
bitsandbytes
quantized
4bit
4-bit precision
Model card Files
xet
 Community
1

Does it support VLLM inference?

#1
by DuDuDuZzz - opened
Discussion
DuDuDuZzz

Does it support VLLM inference? Could you share the quantization script?Thanks！😀
divyajot5005
 Owner

yes it does. Script is available on the linkedin Github

Sign up or log in to comment