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.

Running an LLM without NVIDIA hardware with llama.cpp v1.0.0

Use this resource to run an LLM on CPU, Apple Silicon or non-NVIDIA GPUs

New

  • 436 downloads
  • 138 likes
  • 131 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llama-cpp-local-cpu-inference

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 guides you through building llama.cpp with Metal, CUDA or ROCm depending on your hardware, downloading or converting a GGUF model, then running it. It also covers quantization and the server.

Mostly picked by

Updated November 2, 2026

Card for the “Running an LLM without NVIDIA hardware with llama.cpp” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: building, downloading GGUF models and a first run
  • references/quantization.md, optimization.md and server.md: quantization, optimization and server

Good fit for

  • You want a local LLM without an NVIDIA card
  • You deploy to a low-resource device

Not for

    Tags

    • local inference
    • cpu
    • gguf
    • apple silicon

    About

    You say

    “Build llama.cpp with Metal on my Mac and run a quantized Qwen model.”

    Card for the “Running an LLM without NVIDIA hardware with llama.cpp” 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 run an LLM on CPU, Apple Silicon or non-NVIDIA GPUs
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/optimization.md1.7 KB
    • references/quantization.md5 KB
    • references/server.md2.3 KB
    • SKILL.md6 KB

    Origin and licence

    Listed unmodified

    Author
    Orchestra Research
    Source
    github.com/orchestra-research/ai-research-skills/tree/773a52944ba4747a18bd4ae9ade53fff041adcbc/12-inference-serving/llama-cpp
    Licence
    MIT

    Notice

    « llama-cpp » (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.