Loading…
Loading…
Models / Qwen3-TTS-12Hz
GPU memory needed (smallest version of each): Qwen3-TTS-12Hz 0.6B about 1 GB, Qwen3-TTS-12Hz 1.7B about 1 GB. The cheapest runs on Quadro P4000 from $0.07/h right now.
2 models (0.6B to 1.7B) · ↓ 0 downloads a month · from $0.07/h on Quadro P4000 right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Main (onnx-community)onnx-community/Qwen3-TTS-12Hz-0.6B-CustomVoice | ONNX Runtime | 1 MB | 1 GB | $0.07/h Quadro P4000 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Main (Prince-1)Prince-1/Qwen3-TTS-12Hz-1.7B-VoiceDesign | ONNX Runtime | 1 MB | 1 GB | $0.07/h Quadro P4000 |
| Main (onnx-community)onnx-community/Qwen3-TTS-12Hz-1.7B-VoiceDesign | ONNX Runtime | 1 MB | 1 GB | $0.07/h Quadro P4000 |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").