DeepSeek-V4-Flash-MLX-Q4Q8
Deviad/DeepSeek-V4-Flash-MLX-Q4Q8
Tracked by OpenModelStats since August 27, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 182
- Total downloadsCumulative all-time download counter reported by the source platform.
- 6,022
- 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.
- —
- –this week
- Parameters
- 55.5B
- Last source update
- Apr 29, 2026
Downloads over time
Rolling recent-window downloads as reportedLikes over time
Rank among tracked models
Lower is betterNot enough tracked history yet for a chart.
OpenModelStats began tracking this model on 2026-08-27. Charts appear as daily observations accumulate.
Overview
DeepSeek-V4-Flash-MLX-Q4Q8 is a text generation model published by Deviad. OpenModelStats has tracked the model since Aug 27, 2026, most recently observing it 8 min ago.
- Published
- Apr 28, 2026
- Last updated
- Apr 29, 2026
- Library
- mlx
- License
- mit
- Task
- Text Generation
- Parameters
- 55,545,219,026
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- —
mlxsafetensorsdeepseek_v4apple-silicondeepseekdeepseek-v4mixture-of-expertsmoequantized4-bit8-bitaffine
Publisher
DeviadView publisher statistics →Derived from deepseek-ai/DeepSeek-V4-Flash (reported by the source; parent not yet tracked).
Similar models
| Model | DL 30D |
|---|---|
| Nemotron-H-56B-Base-8Knvidia | 13.4K |
| openbuddy-zero-56b-v21.2-32kOpenBuddy | 8,036 |
| DeepSeek-V4-Flash-0731-mlx-4bitToPo-ToPo | 1,456 |
| Kimi-K3-Q2_K-t158-MTPLX-streamingOpensourceWTF | 2,813 |
| Qwen2-57B-A14B-InstructQwen | 13.3K |
| Qwen2-57B-A14BQwen | 9,920 |