Llama-3.1-405B-Instruct-MXFP4-Preview
amd/Llama-3.1-405B-Instruct-MXFP4-Preview
218B parametersLicense: llama3.1
Tracked by OpenModelStats since August 25, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 1,146
- Total downloadsCumulative all-time download counter reported by the source platform.
- 32.8K
- 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.
- 1
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads.
- #24,296
- –this week
- Parameters
- 218B
- Last source update
- Nov 6, 2025
Downloads over time
Cumulative total downloads observed by OpenModelStatsLikes over time
Rank among tracked models
Lower is betterNot enough tracked history yet for a chart.
OpenModelStats began tracking this model on 2026-08-25. Charts appear as daily observations accumulate.
Overview
Llama-3.1-405B-Instruct-MXFP4-Preview is an AI model published by amd. OpenModelStats has tracked the model since Aug 25, 2026, most recently observing it 5h ago.
- Published
- May 30, 2025
- Last updated
- Nov 6, 2025
- Library
- —
- License
- llama3.1
- Task
- —
- Parameters
- 217,581,568,000
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- —
safetensorsllamabase_model:meta-llama/Llama-3.1-405B-Instructbase_model:quantized:meta-llama/Llama-3.1-405B-Instructlicense:llama3.18-bitquarkregion:us
Publisher
amdView publisher statistics →Derived from meta-llama/Llama-3.1-405B-Instruct (reported by the source; parent not yet tracked).
Similar models
| Model | DL 30D |
|---|---|
| command-a-plus-05-2026-bf16CohereLabs | 57K |
| command-a-plus-05-2026-w4a4CohereLabs | 2,973 |
| command-a-plus-05-2026-fp8CohereLabs | 1,311 |
| MiniMax-M3-NVFP4nvidia | 215.7K |
| Qwen3.8-2.4T-A95B-3bit-UVMAXkernelpool | 1,180 |
| Qwen3.5-397B-A17B-MoE-MXFP4amd | 15K |