fp8_dynamic_moe-e2e
nm-testing/fp8_dynamic_moe-e2e
30.5B parameters
Tracked by OpenModelStats since September 13, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 181
- Total downloadsCumulative all-time download counter reported by the source platform.
- 1,249
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +36(increase)
- 3.4%(up) vs baseline
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 0
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads.
- #49,306
- 4142(down 4142 places)this week
- Parameters
- 30.5B
- Last source update
- Oct 12, 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.
- 34.1
- fp8_dynamic_moe-e2e gained 36 downloads during the last seven tracked days.
Downloads over time
Daily gain between consecutive observationsLikes over time
Rank among tracked models
Lower is betterOverview
fp8_dynamic_moe-e2e is an AI model published by nm-testing. OpenModelStats has tracked the model since Sep 13, 2026, most recently observing it Oct 12, 2026.
- Published
- Jul 25, 2026
- Last updated
- Oct 12, 2026
- Library
- —
- License
- —
- Task
- —
- Parameters
- 30,532,122,624
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- 5
safetensorsqwen3_moecompressed-tensorsregion:us
Similar models
| Model | DL 30D |
|---|---|
| Qwen3-30B-A3BQwen | 1.3M |
| Qwen3-30B-A3B-Instruct-2507Qwen | 1M |
| Qwen3-Coder-30B-A3B-InstructQwen | 398.1K |
| Qwen3-Coder-30B-A3B-Instruct-AWQQuantTrio | 272.6K |
| Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8QuantTrio | 159.9K |
| Qwen3-Coder-30B-A3B-Instruct-MLX-4bitlmstudio-community | 114.9K |