dflash2-mlx-quantized-draft
KaedeTai/dflash2-mlx-quantized-draft
mlxLicense: mit
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 699
- Total downloadsCumulative all-time download counter reported by the source platform.
- 699
- 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.
- 2
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads.
- #29,425
- 52(up 52 places)this week
- Parameters
- —
- Last source update
- Aug 22, 2026
Downloads over time
Rolling recent-window downloads as reportedLikes over time
Rank among tracked models
Lower is betterOverview
dflash2-mlx-quantized-draft is an AI model published by KaedeTai. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it 6h ago.
- Published
- Aug 22, 2026
- Last updated
- Aug 22, 2026
- Library
- mlx
- License
- mit
- Task
- —
- Parameters
- —
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- —
mlxqwen3speculative-decodingdflash2apple-siliconquantizationbenchmarkbase_model:Qwen/Qwen3.8-27Bbase_model:quantized:Qwen/Qwen3.8-27Blicense:mit4-bitregion:us
Publisher
KaedeTaiView publisher statistics →Derived from Qwen/Qwen3.8-27B (reported by the source; parent not yet tracked).
Similar models
| Model | DL 30D |
|---|---|
| all-MiniLM-L6-v2sentence-transformers | 247.7M |
| ms-marco-MiniLM-L6-v2cross-encoder | 84.4M |
| bert-base-uncasedgoogle-bert | 79.6M |
| bge-small-en-v1.5BAAI | 67.4M |
| electra-base-discriminatorgoogle | 51.1M |
| paraphrase-multilingual-MiniLM-L12-v2sentence-transformers | 46.8M |