X · @teortaxesTex
· X / Twitter
RT Didier Lopes: TIL that you could track speed of inference over time, very cool – https://artificialanalysis.ai/models/glm-5-2/providers?speed=outpu…
RT Didier LopesTIL that you could track speed of inference over time, very cool - https://artificialanalysis.ai/models/glm-5-2/providers?speed=output-speed-over-timeTom Greenwald: All these GLM 5.2 providers advertise 200+ tok/s. Yet you try them and get 50 tok/sThe top speeds are super impressive. And I love how much