# EAGLE-4

EAGLE-4 replaces a fixed-depth speculative decoding tree with one that widens or deepens level by level using measured GPU verification cost, paired with a lightweight drafter. On NVIDIA B300 with tensor parallelism 4, it reaches 660.6 tokens/s on Fireworks Bench and 622.9 on Prompt Enhancement SpecBench at batch size 1, or 1.63x and 1.85x the fastest alternative; at batch size 8 the advantages are 1.36x and 1.62x. Creative prompt expansion is harder for drafters to predict, yet the tree recovers more usable continuations from that uncertainty.

EAGLE-4 replaces a fixed-depth speculative decoding tree with one that widens or deepens level by level using measured GPU verification cost, paired with a lightweight drafter. On NVIDIA B300 with tensor parallelism 4, it reaches 660.6 tokens/s on Fireworks Bench and 622.9 on Prompt Enhancement SpecBench at batch size 1, or 1.63x and 1.85x the fastest alternative; at batch size 8 the advantages are 1.36x and 1.62x. Creative prompt expansion is harder for drafters to predict, yet the tree recovers more usable continuations from that uncertainty.