# Choose your machine

> Five ways to run the server, from a 16 GB laptop to a 96 GB GPU, and what each one needs.

Source: https://opendecisio.com/docs/quickstart/

Decisio serves the same routes from every path; what changes is the model behind them and the memory it needs. Find what you have below, and follow the link.

 

[Figure: One server, five ways to run it; start from what you have. What you have and the path that fits it: Linux, one NVIDIA card (96 GB, as measured) takes GPU server; Linux, one NVIDIA card, Docker (96 GB, as measured) takes Docker; A Mac with Apple silicon (each base has its own, in Run it) takes Mac with MLX; A laptop with Ollama (8.6 GB for the Gemma base's smallest tag) takes Ollama; Any machine, for development (a small Hugging Face model on the CPU) takes CPU stand-in.]

 

## TL;DR

 

Whatever you have, the CPU stand-in runs. It serves the routes from a small model on the CPU, so it is for development and not the measured system; for a real base, find your machine in the figure and follow its link.

 

```
uv sync --extra dev --frozen
uv run pytest
uv run python -m decisio.serve.vllm_engine --backend hf --model Qwen/Qwen3-0.6B-Base
```

 

Run against the CPU stand-in at v0.11.1 on 2026-10-14: the install and the server start; the unit tests passed in decisio's own CI on this commit.

 

The stand-in serves the routes from a small model on the CPU for development; it is not the measured system.

 

## The five paths

  

| Machine | Path | Memory needed |
| --- | --- | --- |
| Linux with one NVIDIA card | [GPU server](https://github.com/aminry/decisio/blob/v0.11.1/README.md#gpu-server) | a 96 GB card, as measured; each base's weights are in [Choosing a base](https://opendecisio.com/docs/bases/) |
| Linux with one NVIDIA card and Docker | [Docker](https://github.com/aminry/decisio/blob/v0.11.1/README.md#docker) | as the GPU server |
| Mac with Apple silicon | [Mac with MLX](https://github.com/aminry/decisio/blob/v0.11.1/README.md#mac-with-mlx) | each base's, in [docs/running.md](https://opendecisio.com/docs/quickstart/mac-mlx/) |
| Mac, Linux or Windows with Ollama | [Ollama](https://github.com/aminry/decisio/blob/v0.11.1/README.md#ollama) | 8.6 GB for the Gemma base's smallest tag, so a 16 GB laptop; each tag's size is on its model page ([decisio-gemma](https://ollama.com/aminroudaki/decisio-gemma), [decisio](https://ollama.com/aminroudaki/decisio)) |
| Any machine, for development | [CPU stand-in](https://opendecisio.com/docs/quickstart/) | a small Hugging Face model on the CPU |

 

[`docs/running.md`](https://github.com/aminry/decisio/blob/v0.11.1/docs/running.md) has the details of every path.

 

## What next

 

- [Get started](https://opendecisio.com/docs/): send a first question to the CPU stand-in, on any machine.
- [Choosing a base](https://opendecisio.com/docs/bases/): which of the three models to serve, and when.
- [Flags and options](https://opendecisio.com/docs/flags/): every flag and its default per base.