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.

Estimating memory needed for a model v1.0.0

Use this resource to estimate the memory needed to load an inference model

New

  • 500 downloads
  • 184 likes
  • 240 saves

Free

Install with the CLI

In a terminal, from the folder you want:

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

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 the hf-mem tool on a Hub model ID. The tool reads file headers through partial HTTP requests, without loading the weights, then computes weight memory and optionally KV cache memory. You get the estimate and what you need to check whether the model fits on your GPU.

Mostly picked by

Updated November 2, 2026

Card for the “Estimating memory needed for a model” 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, prerequisites (uv, HF_TOKEN) and commands
  • SKILL.md: estimation examples for Safetensors and GGUF models

Good fit for

  • You are wondering whether a model fits in your card's VRAM
  • You are choosing a cloud instance for a Hub model

Not for

    Tags

    • vram
    • memory
    • gguf
    • safetensors
    • inference

    About

    You say

    “How much VRAM do I need to run this GGUF model for inference with an 8k cache?”

    Card for the “Estimating memory needed for a model” skill

    Skill published by waybarrios 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 load an inference model
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md3.4 KB

    Origin and licence

    Listed unmodified

    Author
    waybarrios
    Source
    github.com/waybarrios/opencode-power-pack/tree/c3328ad1633c1561026532f29b718a2380bc52ee/skills/hf-mem
    Licence
    Apache-2.0

    Notice

    « hf-mem » (waybarrios, 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.