I designed a bfloat16/FP8 alternative in a week using LLMs (arxiv.org)

[dead]

The "Block-Scale-Free" property is the most compelling part here. Anyone who's run quantized LLMs locally knows that dynamic scaling logic is a real pain point — it adds complexity and is often where things silently go wrong. Trading that for QAT-first deployment seems like a reasonable bargain, especially for edge inference where you want the simplest possible hardware path. Curious whether AF8 has been tested against GGUF Q8_0 on any standard benchmarks.