llama-cpp

llama-cpp is a skill for Claude Code, Codex from liortesta/ClawdAgent. It costs 76 tokens per session (1,928 once invoked), scanned A, a copy of llama-cpp, Apache-2.0.

A lightweight C and C++ library for running language models on CPUs, Apple Silicon, and GPUs that do not use NVIDIA CUDA.

In plain words
What is it for?
Use it for local or edge text generation, including CPU-only machines, Apple Silicon, AMD or Intel GPUs, and embedded systems.
Why use it?
It lets you run models on ordinary computers, Macs, and edge devices when a CUDA-based setup is unavailable or unnecessary.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/liortesta/clawdagent/llama-cpp
Any agent
npx skills add liortesta/ClawdAgent --skill llama-cpp
Clone the repo
git clone --depth 1 https://github.com/liortesta/ClawdAgent

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.

agentmods badge for llama-cpp

README.md
[![agentmods](https://agentmods.dev/badge/skills/liortesta/clawdagent/llama-cpp.svg)](https://agentmods.dev/skills/liortesta/clawdagent/llama-cpp)
Your own site
<a href="https://agentmods.dev/skills/liortesta/clawdagent/llama-cpp"><img src="https://agentmods.dev/badge/skills/liortesta/clawdagent/llama-cpp.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,928 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00076 $0.01928
Opus 5 $0.00038 $0.00964
Sonnet 5 $0.00015 $0.00386
Haiku 4.5 $0.00008 $0.00193

Measured yesterday against content hash d74caa45483f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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.

.claude/skills/12-inference-serving/llama-cpp/SKILL.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

llama.cpp

Pure C/C++ LLM inference with minimal dependencies, optimized for CPUs and non-NVIDIA hardware.

When to use llama.cpp

Use llama.cpp when:

  • Running on CPU-only machines
  • Deploying on Apple Silicon (M1/M2/M3/M4)
  • Using AMD or Intel GPUs (no CUDA)
  • Edge deployment (Raspberry Pi, embedded systems)
  • Need simple deployment without Docker/Python

Use TensorRT-LLM instead when:

  • Have NVIDIA GPUs (A100/H100)
  • Need maximum throughput (100K+ tok/s)
  • Running in datacenter with CUDA

Use vLLM instead when:

  • Have NVIDIA GPUs
  • Need Python-first API
  • Want PagedAttention

Quick start

Installation

# macOS/Linux
brew install llama.cpp

# Or build from source
git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp
make

# With Metal (Apple Silicon)
make LLAMA_METAL=1

# With CUDA (NVIDIA)
make LLAMA_CUDA=1

# With ROCm (AMD)
make LLAMA_HIP=1

Download model

# Download from HuggingFace (GGUF format)
huggingface-cli download \
    TheBloke/Llama-2-7B-Chat-GGUF \
    llama-2-7b-chat.Q4_K_M.gguf \
    --local-dir models/

# Or convert from HuggingFace
python convert_hf_to_gguf.py models/llama-2-7b-chat/

Run inference

# Simple chat
./llama-cli \
    -m models/llama-2-7b-chat.Q4_K_M.gguf \
    -p "Explain quantum computing" \
    -n 256  # Max tokens

# Interactive chat
./llama-cli \
    -m models/llama-2-7b-chat.Q4_K_M.gguf \
    --interactive

Server mode

# Start OpenAI-compatible server
./llama-server \
    -m models/llama-2-7b-chat.Q4_K_M.gguf \
    --host 0.0.0.0 \
    --port 8080 \
    -ngl 32  # Offload 32 layers to GPU

# Client request
curl http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-2-7b-chat",
    "messages": [{"role": "user", "content": "Hello!"}],
    "temperature": 0.7,
    "max_tokens": 100
  }'

Quantization formats

GGUF format overview

Format Bits Size (7B) Speed Quality Use Case
Q4_K_M 4.5 4.1 GB Fast Good Recommended default
Q4_K_S 4.3 3.9 GB Faster Lower Speed critical
Q5_K_M 5.5 4.8 GB Medium Better Quality critical
Q6_K 6.5 5.5 GB Slower Best Maximum quality
Q8_0 8.0 7.0 GB Slow Excellent Minimal degradation
Q2_K 2.5 2.7 GB Fastest Poor Testing only

Read the full file on GitHub · 259 lines

Files

What ships with it

3 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.

  1. yesterday First seen · 259 lines · 76 tokens per session scan A d74caa45483f

Subscribe to this mod's changes

llama-cpp is a skill published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 8d ago), licensed Apache-2.0. It adds 76 tokens to every session and 1,928 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

llama-cpp

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

davila7/claude-code-templates · 76 tokens

llama-cpp

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

OpenLAIR/dr-claw · 76 tokens

llama-cpp

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

synthetic-sciences/openscience · 76 tokens

llama-cpp

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

Orchestra-Research/AI-Research-SKILLs · 76 tokens

llama-cpp

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

OpenLAIR/dr-claw-plugin-cc · 76 tokens

llama-cpp

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

ihatesea69/HieuNghi-AI-Skills · 76 tokens