In preliminary single-request benchmarks on 4× NVIDIA B300 GPUs, EAGLE-4 reached 619 tokens/s on Nemotron 3.5 Super VL vs 229 with vanilla decoding.
Eagle blog
Posts
Blog
Read More: EAGLE-4 Delivers 2.7× Faster Decoding for NVIDIA Nemotron 3.5 Super VL in Preliminary Benchmarks
Operate AI at the fastest speed possible today