Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
qwen3-tts-0.6b-q4k-compressed – AI Model by HamzaBrh | AlphaNeural AI
You can deploy this model and start earning money today!
HamzaBrh
/
qwen3-tts-0.6b-q4k-compressed
like
0
tts
qwen3-tts
quantized
en
zh
pt
es
fr
mit
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Qwen3-TTS 0.6b — 0.6b-q4k-compressed
Q4_K backbone + INT8 CP + CPU offload (1.1 GB VRAM, 986 MB disk)
Quantization Config
Parameter
Value
Backbone
q4k
Code Predictor
int8
Vocoder CPU
True
Text Embed Offload
True
Performance
Metric
Value
VRAM
? MB
RTF
0.153 (6.5x real-time)
Weight Storage
986 MB
Quality (Seed-TTS EN)
Metric
Value
WER (EN)
2.39%
Based On
Qwen3-TTS-12Hz-0.6B-Base
Built with
MegaQwen TTS
