106 days of daily snapshots
Trending open models
Ranked by 7-day download growth from our own nightly snapshots — history Hugging Face itself doesn't show.
All tasks
text-generation
text-to-image
image-text-to-text
ASR
sentence-similarity
text-classification
translation
feature-extraction
image-classification
text-to-speech
token-classification
summarization
audio-classification
image-segmentation
object-detection
audio-text-to-text
any-to-any
| # | Model | 30d | Δ 7d | Trend |
|---|---|---|---|---|
| 01 | Breeze-TTS-2.cpp | 1.0 M | ▲ 38.0% | |
| 02 | Qwen3-TTS-GGUF | 1.2 M | ▲ 28.5% | |
| 03 | Drama-3-GGUF | 496 K | ▲ 26.2% | |
| 04 | Higgs-Audio-v3-Studio | 1.1 M | ▲ 21.3% | |
| 05 | OmniVoice | 3.5 M | ▲ 21.0% | |
| 06 | Qwen3-TTS-12Hz-1.7B-VoiceDesign | 608 K | ▲ 13.8% | |
| 07 | kokoro-inno-clone-tuner | 1.6 M | ▲ 11.7% | |
| 08 | audio.cpp-gguf | 8.9 M | ▲ 11.1% | |
| 09 | Qwen3-TTS-12Hz-0.6B-Base | 842 K | ▲ 10.1% | |
| 10 | Kokoro-82M | 12.5 M | ▲ 9.6% | |
| 11 | VieNeu-TTS-v3-Turbo | 2.1 M | ▲ 9.5% | |
| 12 | Kokoro-82M-v1.0-ONNX | 808 K | ▲ 9.3% | |
| 13 | chatterbox | 2.4 M | ▲ 8.9% | |
| 14 | sanoTTS | 559 K | ▲ 7.7% | |
| 15 | F5-TTS | 1.3 M | ▲ 4.8% | |
| 16 | VoxCPM2 | 987 K | ▲ 1.9% |
Snapshots taken nightly at 04:00 UTC from the public Hugging Face API. Also available as JSON: /api/v1/trending · methodology