What GPU do I need to run Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice?
1.9B parameters, published in BF16. View on Hugging Face
Qwen3-TTS-12Hz-1.7B-CustomVoice is published by Qwen on Hugging Face, with 1,208,588 downloads and 2,233 likes to date. It's a Qwen3TTSForConditionalGeneration model built for text-to-speech, published natively in BF16.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 3.6 GB | 4.3 GB | RTX 3070 | 1 | $0.088/hr |
| FP8 (quantized) | 1.8 GB | 2.1 GB | RTX 5060 Ti | 1 | $0.180/hr |
| INT4 (quantized) | 0.9 GB | 1.1 GB | RTX 3070 | 1 | $0.088/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run Qwen3-TTS-12Hz-1.7B-CustomVoice at its published (BF16) precision: 1× RTX 3070, at $0.088/hr per GPU ($0.088/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Qwen3-TTS-12Hz-1.7B-CustomVoice: common questions
How much VRAM does Qwen3-TTS-12Hz-1.7B-CustomVoice need?
4.3 GB at BF16, 2.1 GB at FP8 (quantized), 1.1 GB at INT4 (quantized). All of those sit under 6 GB, the smallest capacity this page reasons about, so VRAM is not what limits where this model runs. The 3.6 GB of weights plus inference overhead is the whole requirement.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Qwen3 models
- Qwen3-1.7B (2.0B, BF16)
- Qwen3-1.7B-FP8 (2.0B, F8_E4M3)
- Qwen3-ASR-1.7B-hf (2.0B, BF16)
- Confucius4-R2T2 (2.0B, BF16)
- Qwen3-VL-2B-Instruct (2.1B, BF16)
Alternatives at this size
Other models for text-to-speech within about a third of Qwen3-TTS-12Hz-1.7B-CustomVoice's 1.9B parameters, from other model lines.
- VoxCPM2 (2.3B, BF16)
- VibeVoice-1.5B (2.7B, BF16)
- Dia-1.6B (1.6B, F32)
- Ming-3.0-tts-0.5B (1.5B, BF16)
- parler-tts-large-v1 (2.3B, F32)
More on Qwen3-TTS-12Hz-1.7B-CustomVoice
Fits on an 8 GB GPU at BF16: every model that fits in 8 GB.
Best text-to-speech models: how Qwen3-TTS-12Hz-1.7B-CustomVoice ranks against the rest.
Related reading: RTX 3070 pricing and specs, Whisper variants compared, and What AI inference is.
Your own GPU cloud accounts
One console for the GPU clouds you already rent from. Your keys stay on your machine.
$20 a month, flat