Mean accepted length and draft accept rate measured end-to-end against MiniMaxAI/MiniMax-M3-MXFP8 served with vLLM at tensor-parallel-size=4, num_speculative_tokens=3, greedy sampling (temperature=0, top_p=1.0), max-concurrency=16.

Dataset	n	Mean accepted length	Draft accept rate	Per-position accept rate (pos 1 / 2 / 3)
MT-Bench	64	2.663	55.42%	0.742 / 0.534 / 0.386
SPEED-Bench (qualitative)	64	2.633	54.43%	0.736 / 0.526 / 0.371

Inferact/MiniMax-M3-EAGLE3-GQA-NVFP4

MiniMax-M3-EAGLE3-GQA-NVFP4

Performance

Inferact/
MiniMax-M3-EAGLE3-GQA-NVFP4