comsat-embed-ja-8b-preview
sionic-ai/comsat-embed-ja-8b-preview
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 2,122
- Total downloadsCumulative all-time download counter reported by the source platform.
- 2,297
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- —
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 0
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #422 among tracked Sentence Similarity models.
- #16,887
- –this week
- Parameters
- 7.6B
- Last source update
- Jul 5, 2026
Downloads over time
Daily gain between consecutive observationsNot enough tracked history yet for a chart.
OpenModelStats began tracking this model on 2026-08-24. Charts appear as daily observations accumulate.
Likes over time
Not enough tracked history yet for a chart.
OpenModelStats began tracking this model on 2026-08-24. Charts appear as daily observations accumulate.
Rank among tracked models
Lower is betterNot enough tracked history yet for a chart.
OpenModelStats began tracking this model on 2026-08-24. Charts appear as daily observations accumulate.
Overview
comsat-embed-ja-8b-preview is a sentence similarity model published by sionic-ai. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it 35 min ago.
- Published
- Jul 3, 2026
- Last updated
- Jul 5, 2026
- Library
- sentence-transformers
- License
- cc-by-nc-4.0
- Task
- Sentence Similarity
- Parameters
- 7,567,295,488
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- —
sentence-transformerssafetensorsqwen3feature-extractionsentence-similaritymtebjapaneseretrievaljaenbase_model:Qwen/Qwen3-Embedding-8Bbase_model:finetune:Qwen/Qwen3-Embedding-8B
Publisher
sionic-aiView publisher statistics →Derived from Qwen/Qwen3-Embedding-8B (reported by the source; parent not yet tracked).
Similar models
| Model | DL 30D |
|---|---|
| Octen-Embedding-8BOcten | 19K |
| Octen-Embedding-8B-INT8Octen | 1,279 |
| comsat-embed-ko-8b-previewsionic-ai | 420 |
| MathLeap-Qwen-8Buw-math-ai | 400 |
| BGE-VL-v1.5-mmebBAAI | 4,125 |
| gte-Qwen2-7B-instructAlibaba-NLP | 118.6K |