EAGLE-4
Eagle is the fastest speculative decoding that exists, used by everyone.
EAGLE-4 launched on 20 October 2026. It ranked #79 on Daily Launch on 23 October 2026 with a Launch Score of 32, from +151 stars on 23 Oct on GitHub. It moved down 56 places from the day before.
What is EAGLE 4?
Leave speculation on. EAGLE-4 adapts to your hardware, batch and workload. EAGLE-4 (Extrapolation Algorithm for Greater Language-model Efficiency) speeds up LLM inference with speculative decoding. EAGLE-4 draft models are built to run with eagle-harness, which decides how far to speculate from measured costs on your setup, so every draft tree fits the batch size, the hardware and the workload. The output stays exactly what the target model would generate on its own: up to 3.4× faster generation on Qwen3.8-27B, with the same answers.
From its README on GitHub
EAGLE 4 (EAGLE-4) is a repo by eagle-hq on GitHub. It is written in Python.
How to get EAGLE 4
docker run --gpus all --ipc host -p 127.0.0.1:30000:30000 -e HF_HOME=/hf -v ~/.cache/huggingface:/hf ghcr.io/eagle-hq/eagle-4-sglang:0.1.3 sglang serve --model-path Qwen/Qwen3.8-27B --host 0.0.0.0 --disable-overlap-schedule --speculative-algorithm EAGLE_HARNESS --speculative-draft-model-path EAGLE-Corp/Qwen3.8-27B-EAGLE4 --speculative-num-steps 12 --speculative-eagle-topk 4 --speculative-num-draft-tokens 16 --speculative-algorithm-config '{}'From its README on GitHub
More steps and the source are in its repository on GitHub.
Screenshot of eagle.ai
In its own words
Official Inference Code of EAGLE-4
From its GitHub repository