/quickstart

from install to first token

Name: mullama
Author: Cognisoc

One dependency, no daemon required. Install it, run a model, or link it straight into your app.

// step 1 — install

install

curl -fsSL https://mullama.cognisoc.com/install.sh | sh

cargo add mullama

pip install mullama

npm install mullama

go get github.com/cognisoc/mullama

composer require mullama/mullama

docker pull ghcr.io/cognisoc/mullama

Windows: iwr -useb https://mullama.cognisoc.com/install.ps1 | iex.

GPU builds set an env var before building from source (LLAMA_CUDA=1, LLAMA_METAL=1, LLAMA_HIPBLAS=1, LLAMA_VULKAN=1, LLAMA_CLBLAST=1, LLAMA_SYCL=1, LLAMA_RPC=1) or use the -cuda container tag.

// step 2 — run

run a model

~/dev — mullama run llama3.2:1b

$ mullama run llama3.2:1b "What is the capital of France?"

pulling manifest... 100%

resolving llama3.2:1b -> hf:bartowski/Llama-3.2-1B-Instruct-GGUF

backend: Metal · ctx: 4096 · model loaded in 412ms

The capital of France is Paris.

$ _

// step 3 — serve

serve an API

# OpenAI + Anthropic compatible on :11434
mullama serve --model llama3.2:1b

export OPENAI_BASE_URL=http://localhost:11434/v1
export ANTHROPIC_BASE_URL=http://localhost:11434
# openai-py, anthropic-py, LangChain, LlamaIndex — unchanged

// or — embed

embed in-process

Skip the daemon: load a model and generate directly from your language of choice. See the features page for the full binding list and the docs for the API reference.

see code examples → full docs