model

eagle3_qwen3_8b_ttt7

modelactiveprovisionaleagle3-qwen3-8b-ttt7-0996b131·1 events·first seen 11h ago

Aliases: eagle3_qwen3_8b_ttt7

Co-occurring entities

Eagle3 DeepSeek V4 Qwen3-4B Hugging Face

More like this (12)

eagle3_qwen3_14b_ttt7 Eagle3 Qwen3.6-35B-A3B Qwen3.5-35B-A3B Qwen3.6-27B Qwen3-30B-A3B-Base Qwen3-ASR-0.6B Qwen3.5-122B-A10B Qwen3-14B Qwen3.5-0.8B Qwen3-30B Qwen3.5-35B-A3B-Base

Recent events (1)

3Deepseek·11h ago·source ↗

DeepSeek releases EAGLE3 speculative decoding draft model for Qwen3-8B

DeepSeek published eagle3_qwen3_8b_ttt7 on Hugging Face, a draft model for EAGLE3 speculative decoding targeting the Qwen3-8B base model. EAGLE3 is DeepSeek's third-generation speculative decoding framework designed to accelerate inference by predicting future tokens with a lightweight draft head. The release is a narrow inference optimization artifact with minimal engagement at time of indexing.

Inference Economics Eagle3 DeepSeek V4 Qwen3-4B +2 more