PowerBeef02/Qwen3-TTS-12Hz-1.7B-VoiceDesign-hybrid-attn
text-to-speech model by PowerBeef02
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Vocello production artifact: a mixed-precision derivative of Qwen3-TTS (Apache-2.0), assembled tensor by tensor from two Vocello artifacts of the same MLX conversion, with no requantization: (affine 4-bit, group size 64); PowerBeef02/Qwen3-TTS-12Hz-1.7B-VoiceDesign-8bit at revision bb56faf7920923e0ca398798e6b2515b5fcde503 (affine 8-bit, group size 64), 176 MB more weights. config.json names each of those modules under quantization. Every other tensor, the code predictor's included, is the 4-bit artifact's own, and so is every file but this card, config.json and the index: the speech tokenizer, and marking/, which holds Meta's AudioSeal generator (MIT licence), unchanged. Chosen by machine screens recorded before their takes, on a Mac…
Read the full model card ↗ · Preview checked 2026-11-13T09:02:16.979Z
Inside the original model card — Document outline
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
PowerBeef02/Qwen3-TTS-12Hz-1.7B-VoiceDesign-hybrid-attn is a text-to-speech model repository published by PowerBeef02 on Hugging Face. The source reports the mlx-audio library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-to-speech
- Library
- mlx-audio
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 2,580,162,816
- Architecture
- Qwen3TTSForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-11-13T06:33:12.000Z
- Last modified
- 2026-11-13T06:34:07.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: PowerBeef02/Qwen3-TTS-12Hz-1.7B-VoiceDesign-4bit, PowerBeef02/Qwen3-TTS-12Hz-1.7B-VoiceDesign-8bit
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-13T06:57:58.356Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.