[{"data":1,"prerenderedAt":152},["ShallowReactive",2],{"project-46724565":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":10,"maker":11,"posted_at":12,"year":13,"points":14,"comments":15,"rank_in_year":16,"shown_in_year":17,"top":18,"tier":19,"category":20,"subcategory":21,"format":22,"keywords":23,"reception":29,"sentiment":30,"stance_mix":31,"scored_comments":35,"aspects":36,"strip":39,"post_text":30,"what":41,"said":52,"maker_in_thread":99,"shape":102,"grid":105,"attempts":114,"same_week":115,"maker_shows":144,"maker_hidden":145,"reader_version":146,"card":147},"46724565","coreml-cli","CLI for working with Apple Core ML models","title","Show HN: CLI for working with Apple Core ML models","https:\u002F\u002Fgithub.com\u002Fschappim\u002Fcoreml-cli","github.com","schappim",1769112746,2026,48,5,1246,4366,29,"shown","ai","model runtime cli","cli",[24,25,26,27,28],"core ml","apple silicon","ml benchmarking","swift cli","on-device inference","quiet",null,{"positive":32,"neutral":33,"mixed":34,"critical":33},2,1,0,4,{"idea":37,"performance":38},{"positive":32,"critical":34},{"positive":34,"critical":33},[15,40,34,15,33],3,{"problem":30,"audience":30,"pricing":30,"motivation":30,"time_to_build":30,"stack":42,"openness":51,"stage":51,"team_size":51},[43],{"value":44,"source":45,"evidence":46},"Swift","commenter",[47],{"id":48,"by":49,"text":50},"46727013","pzo","> It supports the conversion of PyTorch, TF\u002FTF Lite, ONNX I think it doesn't support TF Lite (on TF SavedModels) and ONNX haven't been supported anymore for quite a while sadly…","unknown",{"praise":53,"objections":62,"requests":70,"questions":79,"alternatives":91},[54],{"value":55,"source":45,"evidence":56},"Commenters like the project and its Swift approach, which may reduce benchmarking overhead",[57,61],{"id":58,"by":59,"text":60},"46728007","malshe","Looks really nice. I plan to try it out this weekend. I am not familiar with all the Core ML models. Where can I get their names to try out?",{"id":48,"by":49,"text":50},[63],{"value":64,"source":45,"evidence":65},"CLI reloads the model on every invocation, adding latency compared to a persistent service",[66],{"id":67,"by":68,"text":69},"46733937","storystarling","The JSON output makes it easy to wrap as a tool for frameworks like LangGraph, but I would be worried about the latency. Since it is a CLI, you are likely reloading the whole…",[71,75],{"value":72,"source":45,"evidence":73},"Add an agent skill version",[74],{"id":48,"by":49,"text":50},{"value":76,"source":45,"evidence":77},"Parse Xcode performance reports into human-readable output",[78],{"id":48,"by":49,"text":50},[80,87],{"value":81,"source":45,"evidence":82},"Does it handle conversion and quantization from PyTorch or only run existing Core ML files?",[83],{"id":84,"by":85,"text":86},"46726375","dsrtslnd23","Does this handle conversion and quantization from PyTorch? Or is it strictly for running existing Core ML files?",{"value":88,"source":45,"evidence":89},"Where can I get Core ML model names to try?",[90],{"id":58,"by":59,"text":60},[92],{"value":93,"source":94,"evidence":95},"coremltools (Apple's Python conversion library)","maker",[96],{"id":97,"by":11,"text":98},"46726698","Nope, but Apple released the python lib \"coremltools\"[1] and it can do the conversion. It supports the conversion of PyTorch, TF\u002FTF Lite, ONNX etc... 1.…",{"comments":33,"answered":33,"key":100},[101],{"id":97,"text":98},{"commenters":15,"max_depth":35,"maker_replies":33,"first_comment_mins":103,"lifespan_hours":104},186,20,[106,108,110,111,112],[58,34,15,107,59,34],"project\u002Fpositive\u002Fidea",[84,33,40,109,85,34],"project\u002Fneutral\u002Fidea",[97,33,34,109,11,33],[48,33,15,107,49,34],[67,33,33,113,68,34],"project\u002Fcritical\u002Fperformance",[],[116,120,125,130,134,139],{"id":117,"name":118,"points":119,"category":20},"46721802","isometric.nyc",1325,{"id":121,"name":122,"points":123,"category":124},"46793693","HN Arcade",352,"consumer_social",{"id":126,"name":127,"points":128,"category":129},"46779522","one-agent-one-browser",324,"dev_tools",{"id":131,"name":132,"points":133,"category":124},"46802254","Moltbook",287,{"id":135,"name":136,"points":137,"category":138},"46731432","Whosthere",278,"infrastructure",{"id":140,"name":141,"points":142,"category":143},"46753301","Bonsplit",245,"languages",8,false,"v2",{"id":148,"name":5,"line":6,"ai":145,"cat":20,"year":13,"points":14,"comments":15,"rec":29,"s":30,"top":18,"kw":149,"maker":11,"domain":10,"tier":19,"attempts":34,"strip":150,"url":9,"mix":151,"praise":55,"objection":64,"sub":21},46724565,[24,25,26,27,28],"53051",[32,33,34,33],1793991141472]