‹ BackHN Continuity

Thread

Show HN: Cactus Needle 3: 8-29MB automation models can match DeepSeek V4 Flash

236 points · 93 comments · HenryNdubuaku

  1. neilellis · · focus · HN ↗
    Also FYI doesn't run inference on Apple GPU (only for training)
    1. HenryNdubuaku · · focus · HN ↗
      Hey there, yep we found that on Apple devices specifically running on CPU is fast enough that Metal support is not needed. Thanks for flagging this though, and if usecases that would benefit from Metal support come up we will be adding it to the binaries.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.