---
title: "llama.cpp + GGUF - Air Market"
description: "You want to run an AI model on your own computer instead of calling an online service. This uses llama.cpp to run models saved in the GGUF format locally, and helps you find models to try on the Hugg…"
canonical: "https://airmarket.ai/app/llama-cpp"
---

[Air Market](/) / [Data & Analytics](/category/data) / llama.cpp + GGUF

Skill by [Nous Research](/@nousresearch)

# llama.cpp + GGUF

Run AI models on your own machine and find new ones to try

## What this does

You want to run an AI model on your own computer instead of calling an online service. This uses llama.cpp to run models saved in the GGUF format locally, and helps you find models to try on the Hugging Face Hub. Use it when you want models running on your own hardware.

### Top 3 things it does for you

- Run a GGUF model on my own machine
- Find models on the Hugging Face Hub to run

## Information

**llama.cpp + GGUF at a glance**

|  |  |
| --- | --- |
| Kind | Skill |
| Publisher | [Nous Research](/@nousresearch) |
| Category | [Data & Analytics](/category/data) |
| Works with | Agent Skills - an open standard supported by 40+ agents |
| Version | 2.1.2 |
| Size | 43 KB |
| Licence | MIT |
| Repository | [NousResearch/hermes-agent](https://github.com/NousResearch/hermes-agent/tree/5089596685826ef2f63214f2fd184da88cc4cdb7/skills/mlops/inference/llama-cpp) |
| GitHub stars | 261,931 (as of Nov 2026) |

## Security report

**Verified.** AIR scanned this exact version of llama.cpp + GGUF and flagged nothing. AIR's verdict: **safe**.

**What llama.cpp + GGUF's check was run against**

|  |  |
| --- | --- |
| Commit | 5089596685826ef2f63214f2fd184da88cc4cdb7 |
| Content hash | e12545aa4e3cab328f209fc855871b77ee9be95c8b38d06f2e671c55110e2329 |
| Files read | [Browse the files at this exact commit](https://github.com/NousResearch/hermes-agent/blob/5089596685826ef2f63214f2fd184da88cc4cdb7/skills/mlops/inference/llama-cpp/SKILL.md) |

A scan is named by the exact content it read, not by a version number. A different version is a different artifact, and nothing here applies to a version AIR has not scanned.

[Read the full security report for llama.cpp + GGUF](/security/llama-cpp)

## About llama.cpp + GGUF

Runs GGUF models locally with llama.cpp, and helps find models on the Hugging Face Hub.

## What's inside

- SKILL.md - instructions
- references/advanced-usage.md - reference
- references/hub-discovery.md - reference
- references/optimization.md - reference
- references/quantization.md - reference
- references/server.md - reference
- references/troubleshooting.md - reference

## Questions

### Is llama.cpp + GGUF safe to install?

AIR scanned this exact version of llama.cpp + GGUF and flagged nothing. AIR's verdict: safe. The verdict is named by the content that was read, at commit 508959668582, so it cannot drift onto a version nobody scanned. The full report is at https://airmarket.ai/security/llama-cpp.

### How do I install llama.cpp + GGUF?

Open https://airmarket.ai/app/llama-cpp on Air Market and use the install action: Air Market hands Claude a prompt naming this exact skill, and Claude sets it up. Source, pinned to the exact commit this listing describes: https://github.com/NousResearch/hermes-agent/tree/5089596685826ef2f63214f2fd184da88cc4cdb7/skills/mlops/inference/llama-cpp. Install from that link, not the branch.

## Related on Air Market

- [More Data & Analytics listings](/category/data)
- [Everything by Nous Research](/@nousresearch)

---

Canonical URL: <https://airmarket.ai/app/llama-cpp>