Llasa-8B
HKUSTAudio/Llasa-8B
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 1,122
- Total downloadsCumulative all-time download counter reported by the source platform.
- 42.2K
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +268(increase)
- 0.7%(up) vs baseline
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 97
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #353 among tracked Text to Speech models.
- #31,991
- 115(up 115 places)this week
- Parameters
- 8.6B
- Last source update
- Mar 9, 2025
- MomentumOpenModelStats' composite rising-model signal (0–100): a percentile blend of absolute 7-day download gains, capped percentage growth, and likes gained. See Methodology.
- 40.3
- Llasa-8B gained 268 downloads during the last seven tracked days.
- It moved from #354 to #353 among tracked Text to Speech models this week.
Downloads over time
Cumulative total downloads observed by OpenModelStatsLikes over time
Rank among tracked models
Lower is betterOverview
Llasa-8B is a text to speech model published by HKUSTAudio. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it 21h ago.
- Published
- Jan 7, 2025
- Last updated
- Mar 9, 2025
- Library
- —
- License
- cc-by-nc-4.0
- Task
- Text to Speech
- Parameters
- 8,567,197,696
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- 38
safetensorsllamaText-to-Speechtext-to-speechzhenarxiv:2502.04128base_model:meta-llama/Llama-3.1-8B-Instructbase_model:finetune:meta-llama/Llama-3.1-8B-Instructlicense:cc-by-nc-4.0region:us
Publisher
HKUSTAudioView publisher statistics →Derived from meta-llama/Llama-3.1-8B-Instruct (reported by the source; parent not yet tracked).
Similar models
| Model | DL 30D |
|---|---|
| MOSS-TTS-v1.5OpenMOSS-Team | 110.1K |
| MOSS-TTSOpenMOSS-Team | 5,586 |
| moss-tts-v1.5-8b-voice-actinglaion | 286 |
| MOSS-TTSD-v1.0OpenMOSS-Team | 9,076 |
| MisoTTSMisoLabs | 0 |
| VibeVoice-7Bvibevoice | 12.1K |