Optimus Teslabot Would Be an Edge Computing Beast
by Brian Wang from NextBigFuture.com on (#76JH5)
Gavin Baker described how in ~3 years (around 2028-2029), a bigger/bulkier iPhone with enough extra DRAM could run a pruned/distilled/quantized version of a frontier model like Gemini 5 (or Grok 4.x / ChatGPT equivalent) at 30-60 tokens per second on-device. This would be free, private, and good enough for most users. An enhanced future iPhone ...