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.

HQQ quantization without calibration data v1.0.0

Use this resource to quantize an LLM without calibration data

New

  • 442 downloads
  • 151 likes
  • 231 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install hqq-calibration-free-quantization

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 configures HQQ, quantizes a layer or a full model through Transformers, then runs the quantized model. You get a compressed model in minutes, ready for vLLM or LoRA tuning.

Mostly picked by

Updated November 2, 2026

Card for the “HQQ quantization without calibration data” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: installation, backends and quantizing a layer or a model
  • references/advanced-usage.md: advanced HQQ configuration
  • references/troubleshooting.md: common issues and fixes

Good fit for

  • You have no dataset to calibrate a quantization
  • You want to quantize quickly to compare several models

Not for

    Tags

    • hqq
    • quantization
    • no calibration
    • llm

    About

    You say

    “Quantize this model to 4 bits with HQQ so I can test it in Transformers, without a calibration set.”

    Card for the “HQQ quantization without calibration data” skill

    Skill published by davila7 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 quantize an LLM without calibration data
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/advanced-usage.md14.3 KB
    • references/troubleshooting.md11.3 KB
    • SKILL.md11.7 KB

    Origin and licence

    Listed unmodified

    Author
    davila7
    Source
    github.com/davila7/claude-code-templates/tree/f57964ebda91cdfb31755661ecea9395f30020f1/cli-tool/components/skills/ai-research/optimization-hqq
    Licence
    MIT

    Notice

    « optimization-hqq » (davila7, 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.