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.

Estimate a Hub model's memory needs v1.0.0

Use this resource to estimate the memory needed to run a Hub model

New

  • 434 downloads
  • 182 likes
  • 184 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install model-memory-estimator

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 runs hf_mem, which reads the weights with partial HTTP requests without loading them locally, then estimates the memory for the weights and an optional KV cache. You learn whether the model fits on your GPU or a given instance.

Mostly picked by

Updated November 2, 2026

Card for the “Estimate a Hub model's memory needs” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md: use cases, requirements and run command
  • SKILL.md: estimation examples for Safetensors and GGUF

Good fit for

  • You want to know whether a model fits in your graphics card memory
  • You compare two models' memory needs before renting an instance

Not for

    Tags

    • memory
    • VRAM
    • GGUF
    • safetensors

    About

    You say

    “Will this 70-billion-parameter model fit on a 24 GB card?”

    Card for the “Estimate a Hub model's memory needs” skill

    Skill published by huggingface under the Apache-2.0 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 estimate the memory needed to run a Hub model
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md3.3 KB

    Origin and licence

    Listed unmodified

    Author
    huggingface
    Source
    github.com/huggingface/skills/tree/fabc634a893f62ad5c2039830397efa35fa62715/skills/hf-mem
    Licence
    Apache-2.0

    Notice

    « hf-mem » (huggingface, Apache-2.0) 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.