Hermes-4-70B-FP8
NousResearch/Hermes-4-70B-FP8
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 1,192
- Total downloadsCumulative all-time download counter reported by the source platform.
- 77.7K
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +601(increase)
- 0.8%(up) vs baseline
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 43
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #7999 among tracked Text Generation models.
- #30,687
- 251(down 251 places)this week
- Parameters
- 70.6B
- Last source update
- Sep 12, 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.
- 48.5
- Hermes-4-70B-FP8 gained 601 downloads during the last seven tracked days.
- It moved from #7902 to #7999 among tracked Text Generation models this week.
Downloads over time
Cumulative total downloads observed by OpenModelStatsLikes over time
Rank among tracked models
Lower is betterOverview
Hermes-4-70B-FP8 is a text generation model published by NousResearch. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Oct 4, 2026.
- Published
- Aug 18, 2025
- Last updated
- Sep 12, 2025
- Library
- transformers
- License
- llama3
- Task
- Text Generation
- Parameters
- 70,560,423,936
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- 86
transformerssafetensorsllamatext-generationLlama-3.1instructfinetunereasoninghybrid-modechatmlfunction callingtool use
Publisher
NousResearchView publisher statistics →Derived from meta-llama/Llama-3.1-70B (reported by the source; parent not yet tracked).
Similar models
| Model | DL 30D |
|---|---|
| Llama-3.3-70B-Instruct-FP8-dynamicRedHatAI | 119.9K |
| Latxa-Llama-3.1-70B-Instruct-v2-FP8HiTZ | 2,258 |
| DeepSeek-R1-Distill-Llama-70B-FP8-dynamicRedHatAI | 2,130 |
| Llama-3.3-70B-Instruct-quantized.w8a8RedHatAI | 930 |
| Meta-Llama-3.1-70B-Instruct-GPTQ-INT4hugging-quants | 360 |
| Meta-Llama-3-70B-Instruct-FBGEMM-nonuniformnm-testing | 653 |