Llama-3-Smaug-8B
abacusai/Llama-3-Smaug-8B
Tracked by OpenModelStats since September 7, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 8,651
- Total downloadsCumulative all-time download counter reported by the source platform.
- 349.5K
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +2,100(increase)
- 0.6%(up) vs baseline
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 90
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #2162 among tracked Text Generation models.
- #8,890
- 54(down 54 places)this week
- Parameters
- 8B
- Last source update
- May 19, 2024
- MomentumOpenModelStats' composite rising-model signal (0–100): a percentile blend of absolute 7-day download gains, capped percentage growth, and likes gained. See Methodology.
- 55.3
- Llama-3-Smaug-8B gained 2,100 downloads during the last seven tracked days.
- It moved from #2152 to #2162 among tracked Text Generation models this week.
Downloads over time
Rolling recent-window downloads as reportedLikes over time
Rank among tracked models
Lower is betterOverview
Llama-3-Smaug-8B is a text generation model published by abacusai. OpenModelStats has tracked the model since Sep 7, 2026, most recently observing it 27h ago.
- Published
- Apr 19, 2024
- Last updated
- May 19, 2024
- Library
- transformers
- License
- llama2
- Task
- Text Generation
- Parameters
- 8,030,261,248
- Spaces
- —
- Derivative models
- 1
- Velocity 7D/day
- 300
transformerssafetensorsllamatext-generationconversationaldataset:aqua_ratdataset:microsoft/orca-math-word-problems-200kdataset:m-a-p/CodeFeedback-Filtered-Instructiondataset:anon8231489123/ShareGPT_Vicuna_unfilteredarxiv:2402.13228license:llama2eval-results
Publisher
abacusaiView publisher statistics →Model family
Based on base-model relationships reported by the source's metadata.
Derivative models
Similar models
| Model | DL 30D |
|---|---|
| Llama-3.1-8B-Instructmeta-llama | 6.3M |
| Meta-Llama-3-8B-Instructmeta-llama | 883.3K |
| Llama-3.1-8Bmeta-llama | 636.8K |
| Hermes-3-Llama-3.1-8BNousResearch | 521.6K |
| saiga_llama3_8bIlyaGusev | 405.4K |
| Meta-Llama-3.1-8B-InstructNousResearch | 234.1K |