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.

Quantizing a model without calibration data with HQQ v1.0.0

Use this resource to quantize a model to 4, 3 or 2 bits without a calibration set

New

  • 432 downloads
  • 220 likes
  • 155 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install hqq-calibration-free-quantization-2

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 helps you configure HQQ, quantize a layer or a full model with Transformers, then use it as usual. You get configuration code and backend settings.

Mostly picked by

Updated November 2, 2026

Card for the “Quantizing a model without calibration data with HQQ” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: installation, configuration and quantization
  • references/advanced-usage.md and troubleshooting.md: backends and troubleshooting

Good fit for

  • You have no calibration data
  • You want to quantize quickly to test several variants

Not for

    Tags

    • quantization
    • no calibration
    • llm
    • bits

    About

    You say

    “Quantize this model to 4 bits with HQQ, without a calibration set.”

    Card for the “Quantizing a model without calibration data with HQQ” skill

    Skill published by Orchestra Research 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 a model to 4, 3 or 2 bits without a calibration set
    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.md11.6 KB

    Origin and licence

    Listed unmodified

    Author
    Orchestra Research
    Source
    github.com/orchestra-research/ai-research-skills/tree/773a52944ba4747a18bd4ae9ade53fff041adcbc/10-optimization/hqq
    Licence
    MIT

    Notice

    « hqq-quantization » (Orchestra Research, 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.