A guide for running language models locally with llama.cpp using GGUF model files. It covers choosing model versions for available computer memory and starting a local command-line or server interface.

Use it to discover compatible Hugging Face models, choose quantized files, and create commands for local text generation or an HTTP server.

It helps avoid guessing which model file and size will fit a CPU, Apple Silicon computer, or GPU. It also provides a path from finding a model repository to running it locally.

llama-cpp — Skill for Claude Code and Codex by aivrar

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add aivrar/portable-hermes-agent --skill llama-cpp

Clone the repo

git clone --depth 1 https://github.com/aivrar/portable-hermes-agent

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aivrar/portable-hermes-agent/llama-cpp.svg)](https://agentmods.dev/skills/aivrar/portable-hermes-agent/llama-cpp)

Your own site

<a href="https://agentmods.dev/skills/aivrar/portable-hermes-agent/llama-cpp"><img src="https://agentmods.dev/badge/skills/aivrar/portable-hermes-agent/llama-cpp.svg" alt="Measured on agentmods" height="20"></a>

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,512 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin 100% copy Near-identical to another mod in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00018	$0.02512
Opus 5	$0.00009	$0.01256
Sonnet 5	$0.00004	$0.00502
Haiku 4.5	$0.00002	$0.00251

Measured 4d ago against content hash 9c1ef45f6197, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

llama-cpp scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:8080/v1/chat/completions \

Origin

This is a copy

100% identical to llama-cpp — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/mlops/inference/llama-cpp/SKILL.md · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

llama.cpp + GGUF

Use this skill for local GGUF inference, quant selection, or Hugging Face repo discovery for llama.cpp.

When to use

Run local models on CPU, Apple Silicon, CUDA, ROCm, or Intel GPUs
Find the right GGUF for a specific Hugging Face repo
Build a llama-server or llama-cli command from the Hub
Search the Hub for models that already support llama.cpp
Enumerate available .gguf files and sizes for a repo
Decide between Q4/Q5/Q6/IQ variants for the user's RAM or VRAM

Model Discovery workflow

Prefer URL workflows before asking for hf, Python, or custom scripts.

Search for candidate repos on the Hub:
- Base: https://huggingface.co/models?apps=llama.cpp&sort=trending
- Add search=<term> for a model family
- Add num_parameters=min:0,max:24B or similar when the user has size constraints
Open the repo with the llama.cpp local-app view:
- https://huggingface.co/<repo>?local-app=llama.cpp
Treat the local-app snippet as the source of truth when it is visible:
- copy the exact llama-server or llama-cli command
- report the recommended quant exactly as HF shows it
Read the same ?local-app=llama.cpp URL as page text or HTML and extract the section under Hardware compatibility:
- prefer its exact quant labels and sizes over generic tables
- keep repo-specific labels such as UD-Q4_K_M or IQ4_NL_XL
- if that section is not visible in the fetched page source, say so and fall back to the tree API plus generic quant guidance
Query the tree API to confirm what actually exists:
- https://huggingface.co/api/models/<repo>/tree/main?recursive=true
- keep entries where type is file and path ends with .gguf
- use path and size as the source of truth for filenames and byte sizes
- separate quantized checkpoints from mmproj-*.gguf projector files and BF16/ shard files
- use https://huggingface.co/<repo>/tree/main only as a human fallback
If the local-app snippet is not text-visible, reconstruct the command from the repo plus the chosen quant:
- shorthand quant selection: llama-server -hf <repo>:<QUANT>
- exact-file fallback: llama-server --hf-repo <repo> --hf-file <filename.gguf>
Only suggest conversion from Transformers weights if the repo does not already expose GGUF files.

Read the full file on GitHub · 250 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

4d ago First seen · 250 lines · 18 tokens per session scan A 9c1ef45f6197

Subscribe to this mod's changes

llama-cpp is a skill published in the GitHub repository aivrar/portable-hermes-agent (215 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 2,512 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to llama-cpp, differing in 0 lines, and is treated as a copy.

Data and AI ai ai-agents desktop-app hermes lm-studio local-ai

rag-index-decisions

After making a non-obvious architectural decision, solving a novel bug, agreeing on a coding standard, or reaching a conclusion worth remembering, index it back into the knowledge base so the next occurrence is one search away. Uses adddocument or addfromurl. Closes the feedback loop that makes a RAG-backed team…

lyonzin/knowledge-rag · 72 tokens

rag-cite-sources

Every technical claim drawn from the local corpus must ship with a source citation formatted as path:line or path:section. Trigger whenever the response quotes, paraphrases, or acts on knowledge that came from a searchknowledge or getdocument call. Makes answers auditable and lets the user jump to source in one click.

lyonzin/knowledge-rag · 70 tokens

rag-onboard-context

At the start of every new session or when the topic shifts significantly, probe the knowledge base to learn what is indexed. Calls getindexstats + listcategories + a couple of exploratory searchknowledge queries. Prevents the agent from operating blind or making wrong assumptions about what the corpus contains.

lyonzin/knowledge-rag · 63 tokens

rag-web-fallback

Only reach for external web search when the local corpus comes back empty or clearly insufficient. Forces the agent to try knowledge-rag first, then explicitly document why it needed to escalate. Prevents wasted API cost, latency, and (in air-gapped deployments) accidental network calls.

lyonzin/knowledge-rag · 61 tokens

library-rag

Semantic search over a personal library using Nemotron-3-Embed-1B embeddings + sqlite-vec. Index books, documents, any text corpus; query by meaning. Includes EPUB→Markdown conversion and MCP server for auto-available search tools.

moonlight-lupin/agent-skills · 54 tokens

proxy-local-ai-subscriptions

A guide for exposing your local Codex, ChatGPT Codex, or Claude Code subscription through a protected local OpenAI-compatible endpoint, then connecting it to NextClaw as a custom provider.

Peiiii/nextclaw · 126 tokens

llama-cpp