←Back to NewsAI News/Training InfranewsTraining InfraLlmsMagic Matches DeepSeek V4 Pro Base Using 50x Less ComputeMagic claims a pretraining recipe that matches DeepSeek V4 Pro Base with roughly 50x fewer FLOPs, hitting frontier quality for around $0.5M on GB200.SourceMagicPublishedSep 8, 2026, 4:09 PMAuthorAlphaSignal NewsroomRead1 min readMagic claims a pretraining recipe that matches DeepSeek V4 Pro Base with roughly 50x fewer FLOPs, hitting frontier quality for around $0.5M on GB200.Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.Read original report ↗Next readsAlphaSignal · paperTsinghua's SMELT Cuts AI Training Costs 18% by Looping Layers TwiceHark · newsFigure AI's Brett Adcock Bets Gigawatt NVIDIA Deal on Hark HandoffAlphaSignal · paperOne Hidden Ratio Controls How Fast AI Models Actually Learn
