Llama Cpp

What it does

When your agent uses it

• Tasks that involve LLM inference and serving

Example prompts

• “/llama-cpp”

Requirements

• Python 3
• Docker

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1Search for candidate repos on the Hub
2. 2Open the repo with the llama.cpp local-app view
3. 3Treat the local-app snippet as the source of truth when it is visible
4. 4Read the same ?local-app=llama.cpp URL as page text or HTML and extract the section under Hardware compatibility
5. 5Query the tree API to confirm what actually exists
6. 6If the local-app snippet is not text-visible, reconstruct the command from the repo plus the chosen quant
7. 7Only suggest conversion from Transformers weights if the repo does not already expose GGUF files.

What it can do on your machine

Read from SKILL.md and the folder at commit 7fd2b9a. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • cmake
  • pip
  • brew
  • winget
  • git
  • curl

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • huggingface.co
  • github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Llama Cpp loads about 2.2k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 17 tokens; SKILL.md has 698 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~17

When it runs · the whole SKILL.md, loaded when a task matches

~2.2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~11k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Tommy-yw/RunbookHermes at commit 7fd2b9a, republished under its MIT licence (© Tommy-yw). 698 words, ~2,209 tokens.

name

llama-cpp

description

llama.cpp local GGUF inference + HF Hub model discovery.

version

2.1.2

author

Orchestra Research

license

MIT

dependencies

llama-cpp-python>=0.2.0

# macOS / Linux (simplest)
brew install llama.cpp

winget install llama.cpp

git clone https://github.com/ggml-org/llama.cpp
cd llama.cpp
cmake -B build
cmake --build build --config Release

llama-cli -hf bartowski/Llama-3.2-3B-Instruct-GGUF:Q8_0

llama-server -hf bartowski/Llama-3.2-3B-Instruct-GGUF:Q8_0

llama-server \
    --hf-repo microsoft/Phi-3-mini-4k-instruct-gguf \
    --hf-file Phi-3-mini-4k-instruct-q4.gguf \
    -c 4096

curl http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      {"role": "user", "content": "Write a limerick about Python exceptions"}
    ]
  }'

from llama_cpp import Llama

llm = Llama(
    model_path="./model-q4_k_m.gguf",
    n_ctx=4096,
    n_gpu_layers=35,     # 0 for CPU, 99 to offload everything
    n_threads=8,
)

out = llm("What is machine learning?", max_tokens=256, temperature=0.7)
print(out["choices"][0]["text"])

llm = Llama(
    model_path="./model-q4_k_m.gguf",
    n_ctx=4096,
    n_gpu_layers=35,
    chat_format="llama-3",   # or "chatml", "mistral", etc.
)

resp = llm.create_chat_completion(
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is Python?"},
    ],
    max_tokens=256,
)
print(resp["choices"][0]["message"]["content"])

# Streaming
for chunk in llm("Explain quantum computing:", max_tokens=256, stream=True):
    print(chunk["choices"][0]["text"], end="", flush=True)

llm = Llama(model_path="./model-q4_k_m.gguf", embedding=True, n_gpu_layers=35)
vec = llm.embed("This is a test sentence.")
print(f"Embedding dimension: {len(vec)}")

llm = Llama.from_pretrained(
    repo_id="bartowski/Llama-3.2-3B-Instruct-GGUF",
    filename="*Q4_K_M.gguf",
    n_gpu_layers=35,
)

https://huggingface.co/models?apps=llama.cpp&sort=trending
https://huggingface.co/models?search=<term>&apps=llama.cpp&sort=trending
https://huggingface.co/models?search=<term>&apps=llama.cpp&num_parameters=min:0,max:24B&sort=trending
https://huggingface.co/<repo>?local-app=llama.cpp
https://huggingface.co/api/models/<repo>/tree/main?recursive=true
https://huggingface.co/<repo>/tree/main

Repo: <repo>
Recommended quant from HF: <label> (<size>)
llama-server: <command>
Other GGUFs:
- <filename> - <size>
- <filename> - <size>
Source URLs:
- <local-app URL>
- <tree API URL>

© Tommy-yw, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files (references) in skills/mlops/inference/llama-cpp of Tommy-yw/RunbookHermes.

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

Open the folder on GitHubat commit 7fd2b9a

Used in 4 other repositories

We found 5 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 4 other GitHub owners. This page covers the copy in Tommy-yw/RunbookHermes, which our catalogue first saw on October 7, 2026.

• Luciole-Studio/Misaka-Agentmisaka/core/skills/assets/optional/mlops/inference/llama-cpp
• NousResearch/hermes-agentoptional-skills/mlops/inference/llama-cpp
• johnson7788/MultiUserClawhermes-agent/skills/mlops/inference/llama-cpp
• ArgentAIOS/argentos-coreskills/hermes/mlops/inference/llama-cppskills/community/mlops/inference/llama-cpp