Alibaba (Qwen) · Apache 2.0
Qwen3-TTS
Alibaba’s voice models: clone a voice from 3 seconds, preset voices, or design a voice from a description. 10 languages.
How much memory it needs
Memory to run each model, from its model card or the size of its files. Smaller versions trade some quality for less memory.
| Model | Version | Needs | Business use |
|---|---|---|---|
| Qwen3-TTS 1.7B | Smaller 0.6B model | 2.5 GB | Allowed |
| BF16 | 4.5 GB |
Which computers run it
The best model in this group for each machine.
| Computer | Best version | Fit |
|---|---|---|
| Laptop or PC, no graphics card, 32 GB | Qwen3-TTS 1.7B BF16 | Runs great |
| RTX 4060 · 8 GB | Qwen3-TTS 1.7B BF16 | Runs great |
| RTX 3060 · 12 GB | Qwen3-TTS 1.7B BF16 | Runs great |
| RTX 5060 Ti · 16 GB | Qwen3-TTS 1.7B BF16 | Runs great |
| RTX 4090 · 24 GB | Qwen3-TTS 1.7B BF16 | Runs great |
| RTX 5090 · 32 GB | Qwen3-TTS 1.7B BF16 | Runs great |
| Mac with M4 · 16 GB | Qwen3-TTS 1.7B BF16 | Runs great |
| Mac with M4 Pro · 48 GB | Qwen3-TTS 1.7B BF16 | Runs great |
| Mac with M5 Max · 128 GB | Qwen3-TTS 1.7B BF16 | Runs great |
| Ryzen AI Max+ 395 · 128 GB | Qwen3-TTS 1.7B BF16 | Runs great |
| DGX Spark · 128 GB | Qwen3-TTS 1.7B BF16 | Runs great |
| RTX PRO 6000 · 96 GB | Qwen3-TTS 1.7B BF16 | Runs great |
| Mac Studio with M5 Ultra · 256 GB | Qwen3-TTS 1.7B BF16 | Runs great |
| Mac Studio with M3 Ultra · 512 GB | Qwen3-TTS 1.7B BF16 | Runs great |
What it is good and bad at
Good at
- Voice cloning
- Streaming output
Not good at
- Needs a graphics card for good speed
Start it
- Qwen3-TTS 1.7B: runs in qwen-tts (PyTorch) (also Transformers). Model card