Giga-Retrieval-instruct
ai-sage/Giga-Retrieval-instruct
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 48
- Total downloadsCumulative all-time download counter reported by the source platform.
- 1,376
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +15(increase)
- 1.1%(up) vs baseline
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 6
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #1488 among tracked Embeddings models.
- #54,722
- 439(down 439 places)this week
- Parameters
- 2.5B
- Last source update
- Jun 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.
- 26.4
- Giga-Retrieval-instruct gained 15 downloads during the last seven tracked days.
- It moved from #1493 to #1488 among tracked Embeddings models this week.
Downloads over time
Cumulative total downloads observed by OpenModelStatsLikes over time
Rank among tracked models
Lower is betterOverview
Giga-Retrieval-instruct is a embeddings model published by ai-sage. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Oct 5, 2026.
- Published
- May 29, 2025
- Last updated
- Jun 9, 2025
- Library
- —
- License
- mit
- Task
- Embeddings
- Parameters
- 2,533,494,785
- Spaces
- 1
- Derivative models
- —
- Velocity 7D/day
- 2
safetensorsgigarembedfeature-extractioncustom_coderuenlicense:mitregion:us
Publisher
ai-sageView publisher statistics →Similar models
| Model | DL 30D |
|---|---|
| DiVA-llama-3-v0-8bWillHeld | 192 |
| Qwen3-VL-Embedding-2B-AWQ-4bitLifetimeMistake | 4,100 |
| SFR-Embedding-Code-2B_RSalesforce | 1,394 |
| Qwen3-Embedding-4B-NVFP4andrebadini | 539 |
| WeMM-Embedding-2Btencent | 18.5K |
| WeMM-Embedding-2B-MLX-4bithfadam | 338 |