coreml-cli

AI

model runtime cli

SHOW HN2026

48points
5comments
#1,246of 4,366 in 2026
Top 29%of 2026 by points

How HN took it

QuietFewer than 5 comments about the project

2 positive, 1 neutral or asking, 0 mixed, 1 critical, out of 4 comments about the project.

Idea: 2 for, 0 againstPerformance: 0 for, 1 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Commenters like the project and its Swift approach, which may reduce benchmarking overhead

    From 2 comments
    • 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?
      malshe on HN
    • > It supports the conversion of PyTorch, TF/TF 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…
      pzo on HN

Objections

  • CLI reloads the model on every invocation, adding latency compared to a persistent service

    From 1 comment
    • 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…
      storystarling on HN

Requests

  • Add an agent skill version

    From 1 comment
    • > It supports the conversion of PyTorch, TF/TF 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…
      pzo on HN
  • Parse Xcode performance reports into human-readable output

    From 1 comment
    • > It supports the conversion of PyTorch, TF/TF 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…
      pzo on HN

Questions

  • Does it handle conversion and quantization from PyTorch or only run existing Core ML files?

    From 1 comment
    • Does this handle conversion and quantization from PyTorch? Or is it strictly for running existing Core ML files?
      dsrtslnd23 on HN
  • Where can I get Core ML model names to try?

    From 1 comment
    • 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?
      malshe on HN

Alternatives named

  • coremltools (Apple's Python conversion library)

    From 1 comment
    • Nope, but Apple released the python lib "coremltools"[1] and it can do the conversion. It supports the conversion of PyTorch, TF/TF Lite, ONNX etc... 1.…
      schappim on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/46724565)