Qwen3.8-Flash-Next-MLX-4bit-MTP
Vontra/Qwen3.8-Flash-Next-MLX-4bit-MTP
Tracked by OpenModelStats since September 10, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 3,004
- Total downloadsCumulative all-time download counter reported by the source platform.
- 3,977
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +612(increase)
- 43.0%(up) vs baseline
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 6
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #1699 among tracked Image Text to Text models.
- #16,019
- 95(up 95 places)this week
- Parameters
- 180B
- Last source update
- Sep 8, 2026
- MomentumOpenModelStats' composite rising-model signal (0–100): a percentile blend of absolute 7-day download gains, capped percentage growth, and likes gained. See Methodology.
- 60.9
- Qwen3.8-Flash-Next-MLX-4bit-MTP gained 612 downloads during the last seven tracked days.
- It moved from #1690 to #1699 among tracked Image Text to Text models this week.
Downloads over time
Daily gain between consecutive observationsLikes over time
Rank among tracked models
Lower is betterOverview
Qwen3.8-Flash-Next-MLX-4bit-MTP is a image text to text model published by Vontra. OpenModelStats has tracked the model since Sep 10, 2026, most recently observing it Oct 1, 2026.
- Published
- Aug 26, 2026
- Last updated
- Sep 8, 2026
- Library
- mlx
- License
- other
- Task
- Image Text to Text
- Parameters
- 179,999,981,459
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- 87
mlxsafetensorsqwen4_expmlx-vlmomlxmtpspeculative-decodingqwenqwen3.8qwen4-expmixture-of-expertsvision-language
Publisher
VontraView publisher statistics →Model family
Based on base-model relationships reported by the source's metadata.
Similar models
| Model | DL 30D |
|---|---|
| Qwen3.8-Flash-NextQwen | 1.8M |
| Qwen3.8-Flash-Next-FP8Qwen | 275.8K |
| Qwen3.8-Flash-Next-Uncensored-FP8orcarouter | 19.3K |
| Qwen3.8-Flash-Next-MLX-4bit-MTPTensorFold | 7,458 |
| Qwen3.8-Flash-Next-Uncensored-NVFP4orcarouter | 7,273 |
| Qwen3.8-Flash-Next-GPTQ-4bitbtbtyler09 | 5,301 |