Hermes-4-70B-MLX-8bit
lmstudio-community/Hermes-4-70B-MLX-8bit
70.6B parametersmlx
Tracked by OpenModelStats since September 4, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 51.4K
- Total downloadsCumulative all-time download counter reported by the source platform.
- 924.3K
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +13.5K(increase)
- 1.5%(up) vs baseline
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 2
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads.
- #3,731
- 20(down 20 places)this week
- Parameters
- 70.6B
- Last source update
- Aug 26, 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.
- 63.3
- Hermes-4-70B-MLX-8bit gained 13.5K downloads during the last seven tracked days.
Downloads over time
Rolling recent-window downloads as reportedLikes over time
Rank among tracked models
Lower is betterOverview
Hermes-4-70B-MLX-8bit is an AI model published by lmstudio-community. OpenModelStats has tracked the model since Sep 4, 2026, most recently observing it Oct 4, 2026.
- Published
- Aug 26, 2025
- Last updated
- Aug 26, 2025
- Library
- mlx
- License
- —
- Task
- —
- Parameters
- 70,553,706,496
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- 1,929
mlxsafetensorsllamabase_model:NousResearch/Hermes-4-70Bbase_model:quantized:NousResearch/Hermes-4-70B8-bitregion:us
Publisher
lmstudio-communityView publisher statistics →Derived from NousResearch/Hermes-4-70B (reported by the source; parent not yet tracked).
Similar models
| Model | DL 30D |
|---|---|
| llama-3.3-70b-instruct-awqcasperhansen | 701.6K |
| Llama-3.3-70B-Instructmeta-llama | 399.7K |
| Meta-Llama-3.1-70B-Instruct-AWQ-INT4hugging-quants | 166.7K |
| Llama-3.1-70B-LatamGPT-SFT-1.0latam-gpt | 141.3K |
| Meta-Llama-3-70B-Instructmeta-llama | 119.3K |
| Llama-3.1-70B-Instructmeta-llama | 99.6K |