Qwen3-8B-from-Qwen3-8B_regen-speculators.eagle3-qwen3arch-ckpt1

inference-optimization/Qwen3-8B-from-Qwen3-8B_regen-speculators.eagle3-qwen3arch-ckpt1

1B parametersspeculatorsLicense: apache-2.0
Tracked by OpenModelStats since September 5, 2026View on Hugging Face ↗
Downloads 30D
7,790
Total downloads
60.5K
Gained 7D
+2,178(increase)
4.0%(up) vs baseline
Gained 30D
—
Likes
0
+0 in 7D
Rank · tracked models
#9,441
127(down 127 places)this week
Parameters
1B
Last source update
Jun 10, 2026
Momentum
63.4
  • Qwen3-8B-from-Qwen3-8B_regen-speculators.eagle3-qwen3arch-ckpt1 gained 2,178 downloads during the last seven tracked days.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

Qwen3-8B-from-Qwen3-8B_regen-speculators.eagle3-qwen3arch-ckpt1 is an AI model published by inference-optimization. OpenModelStats has tracked the model since Sep 5, 2026, most recently observing it Oct 5, 2026.

Published
Jun 8, 2026
Last updated
Jun 10, 2026
Library
speculators
License
apache-2.0
Task
—
Parameters
1,022,037,888
Spaces
—
Derivative models
—
Velocity 7D/day
311
speculatorssafetensorseagle3speculative-decodingqwen3custom_codebase_model:Qwen/Qwen3-8Bbase_model:finetune:Qwen/Qwen3-8Blicense:apache-2.0region:us

Publisher

inference-optimizationView publisher statistics →

Derived from Qwen/Qwen3-8B (reported by the source; parent not yet tracked).

Similar models

Models similar to Qwen3-8B-from-Qwen3-8B_regen-speculators.eagle3-qwen3arch-ckpt1
ModelDL 30D
Qwen3-8B-speculator.eagle3RedHatAI15.4K
Speculator-Qwen3-8B-Eagle3-converted-071-quantizednm-testing7,257
Speculator-Qwen3-8B-Eagle3-converted-071-quantized-w4a16nm-testing3,347
Speculator-Qwen3-8B-Eagle3nm-testing1,110
gemma-3-1b-it-bnb-4bitunsloth1,373
deepseek-v4-mini-1B-from-flashkshitijthakkar511
inference-optimization/Qwen3-8B-from-Qwen3-8B_regen-speculators.eagle3-qwen3arch-ckpt1 — Downloads, Growth & Stats | OpenModelStats