Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

On-device AI inference: hardware and constraints v1.0.0

Use this resource to decide whether a model should run on the device rather than in the cloud

New

  • 397 downloads
  • 157 likes
  • 156 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install on-device-ai-architecture

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent compares latency, privacy, cost and offline operation, matches the model to the hardware (microcontroller, NPU, mini-PC) and proposes suitable quantisation. You get a recommendation between on-device, cloud or hybrid.

Mostly picked by

Updated November 2, 2026

Card for the “On-device AI inference: hardware and constraints” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: on-device decision criteria and hardware tiers
  • SKILL.md: architecture levers, quantisation and an on-device, cloud or hybrid recommendation

Good fit for

  • Your voice or real-time app cannot afford a round trip to the cloud
  • Your device must work offline

Not for

    Tags

    • edge
    • on-device
    • npu
    • quantization

    About

    You say

    “A small keyword-spotting model must run on a microcontroller: which hardware and which quantisation?”

    Card for the “On-device AI inference: hardware and constraints” skill

    Skill published by claude-dev-suite under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to decide whether a model should run on the device rather than in the cloud
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md2.4 KB

    Origin and licence

    Listed unmodified

    Author
    claude-dev-suite
    Source
    github.com/claude-dev-suite/claude-dev-suite/tree/e10ab644ba43abe2abc923399226df4af7337214/skills/ai-systems/edge-inference
    Licence
    MIT

    Notice

    « edge-inference » (claude-dev-suite, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.