llama.cpp

The engine almost everything else runs on. Plain C++, no dependencies.

llama.cpp is the C++ engine almost every other local tool wraps. No Python, no dependencies beyond a compiler (or a release binary). `llama-server -hf ggml-org/gpt-oss-120b-GGUF` speaks OpenAI on port 8080.

Context is -c at launch. CPU, Metal, CUDA, ROCm. Use this when you want the metal, or when Ollama and LM Studio are too much app around the model.

Max context: Set with -c at launch
Free tier: Unlimited and private
Requirement: Nothing — no account

Endpoint

Base URLhttp://localhost:8080/v1

Rate limitNone — it is your machine

OpenAI-compatible
text

Code examples

npm install openai

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'http://localhost:8080/v1',
  apiKey: 'not-needed'
})

const response = await client.chat.completions.create({
  model: 'gpt-oss-120b',
  messages: [{ role: 'user', content: 'Explain closures in one paragraph.' }]
})

console.log(response.choices[0].message.content)

pip install openai

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8080/v1",
    api_key="not-needed",
)

response = client.chat.completions.create(
    model="gpt-oss-120b",
    messages=[{"role": "user", "content": "Explain closures in one paragraph."}],
)

print(response.choices[0].message.content)

curl http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-oss-120b",
    "messages": [{"role": "user", "content": "Explain closures in one paragraph."}]
  }'

Worth knowing

Launch the server first: `llama-server -hf ggml-org/gpt-oss-120b-GGUF`.

Models you get for free2

Llama 3.3 70Bllama-3.3-70b
Qwen 3qwen3