Qwen3.8-Flash-Next-heretic2-W4A16-FP8PLE
densohax/Qwen3.8-Flash-Next-heretic2-W4A16-FP8PLE
Tracked by OpenModelStats since September 22, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 3,214
- Total downloadsCumulative all-time download counter reported by the source platform.
- 3,214
- 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.
- 5
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #3993 among tracked Text Generation models.
- #15,468
- 165(up 165 places)this week
- Parameters
- 72.8B
- Last source update
- Sep 22, 2026
- It moved from #4038 to #3993 among tracked Text Generation models this week.
Downloads over time
Cumulative total downloads observed by OpenModelStatsLikes over time
Rank among tracked models
Lower is betterOverview
Qwen3.8-Flash-Next-heretic2-W4A16-FP8PLE is a text generation model published by densohax. OpenModelStats has tracked the model since Sep 22, 2026, most recently observing it 11h ago.
- Published
- Sep 22, 2026
- Last updated
- Sep 22, 2026
- Library
- —
- License
- other
- Task
- Text Generation
- Parameters
- 72,758,053,011
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- —
safetensorsqwen4_expqwen3.8autoroundint4fp8vllmspeculative-decoding256k-contextrtx-3090dual-gpucpu-offload
Publisher
densohaxView publisher statistics →Derived from Qwen/Qwen3.8-Flash-Next (reported by the source; parent not yet tracked).
Similar models
| Model | DL 30D |
|---|---|
| Qwen3.8-Flash-Next-W4A16-FP8PLEalbucino | 6,283 |
| Covenant-72B1Covenant | 57 |
| Qwen2.5-72B-InstructQwen | 287K |
| Qwen2-72BQwen | 25K |
| Qwen2-72B-InstructQwen | 23K |
| Qwen2.5-72BQwen | 18K |