DeepSeek-V4-Flash-MTP-DSpark-MLX
Solstice-AI/DeepSeek-V4-Flash-MTP-DSpark-MLX
Tracked by OpenModelStats since September 7, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 235
- Total downloadsCumulative all-time download counter reported by the source platform.
- 235
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- 0
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 1
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads.
- —
- –this week
- Parameters
- 20.9B
- Last source update
- Sep 7, 2026
Downloads over time
Daily gain between consecutive observationsLikes over time
Rank among tracked models
Lower is betterNot enough tracked history yet for a chart.
OpenModelStats began tracking this model on 2026-09-07. Charts appear as daily observations accumulate.
Overview
DeepSeek-V4-Flash-MTP-DSpark-MLX is a text generation model published by Solstice-AI. OpenModelStats has tracked the model since Sep 7, 2026, most recently observing it Sep 11, 2026.
- Published
- Sep 7, 2026
- Last updated
- Sep 7, 2026
- Library
- mlx
- License
- mit
- Task
- Text Generation
- Parameters
- 20,904,912,743
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- 0
mlxsafetensorsdeepseek_v4_dsparksolstice-aideepseekdeepseek-v4apple-siliconmetalspeculative-decodingmtpdsparktext-generation
Publisher
Solstice-AIView publisher statistics →Derived from deepseek-ai/DeepSeek-V4-Flash-Vision-Exp (reported by the source; parent not yet tracked).
Similar models
| Model | DL 30D |
|---|---|
| gpt-oss-20b-MXFP4-Q8mlx-community | 252.4K |
| gpt-oss-20b-OptiQ-4bitmlx-community | 10.7K |
| gpt-oss-20b-MLX-8bitlmstudio-community | 3,702 |
| gpt-oss-20b-MXFP4-Q4mlx-community | 2,514 |
| OpenAI-gpt-oss-20B-INSTRUCT-Heretic-Uncensored-MXFP4-q8-hi-mlxnightmedia | 2,002 |
| gpt-oss-20b-TurboQuant-MLX-4bitmajentik | 446 |