> ## Documentation Index
> Fetch the complete documentation index at: https://docs.poolside.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# How to run a Poolside coding agent locally
> Run a Poolside coding agent with an open-weight model on your own hardware.
Use Laguna XS.2, Ollama, and Poolside Agent CLI to run a coding agent with an open-weight model on your own hardware. Laguna XS.2 is released under Apache 2.0.
With this setup, Ollama serves the model locally and `pool` connects to it from your project directory. Your code and model traffic stay on the machine where you run the local model server.
## How it works
A local Poolside agent uses four pieces:
* **Laguna XS.2**: The model. Laguna XS.2 has 33B total parameters and 3B active parameters per token.
* **Ollama**: The local runtime. Ollama pulls the model and serves it through an OpenAI-compatible endpoint on your machine.
* **Poolside Agent CLI**: The terminal-based coding agent. Use the `pool` command to work with the local model from your project directory.
* **ACP editors**: Editors compatible with the Agent Client Protocol (ACP), such as JetBrains and Zed, can use the same local agent through ACP.
## Prerequisites
Before you install the local agent, check that your machine has enough memory, GPU support, and disk space for the model you want to run.
### Hardware
Laguna XS.2 can run locally on the following hardware:
| Platform | Status |
| ------------------------------------------------------------------------- | -------------------------------------------- |
| macOS Apple Silicon, M1 and newer | Supported with MLX and Metal through Ollama. |
| Linux with NVIDIA GPUs, 8 GB VRAM and up | Supported with CUDA through Ollama. |
| Linux with DGX Spark or Grace Blackwell systems, including GB10 and GB200 | Supported and sized against unified memory. |
On NVIDIA systems, Blackwell, Hopper, and Ada GPUs are recommended. Turing and older GPUs may work, but they are not recommended.
Use hardware that meets these minimums:
* 32 GB system RAM.
* 8 GB VRAM on discrete NVIDIA GPUs.
* Enough free disk space for the selected model tag plus 8 GB on the Ollama models volume.
### Memory and context
Model weights and KV cache share memory while the model runs. Use a context length that fits the memory available on your machine.
| Total or unified RAM | Default context | Comfortable for |
| -------------------- | ------------------------------------------ | ---------------------------------- |
| 32 to 47 GB | 16K | The default `q4_K_M` quantization. |
| 48 to 63 GB | 32K | `q4_K_M` with working room. |
| 64 to 95 GB | 65K | `q8_0` and longer sessions. |
| 96 GB and up | 65K by default, 256K with `--context 256k` | `bf16` and longer context. |
## Steps
To run a Poolside coding agent locally, set up Ollama, pull Laguna XS.2, install Poolside Agent CLI, and start an agent session from your project directory.
### Step 1: Install Ollama
Install Ollama:
```bash theme={null}
curl -fsSL https://ollama.com/install.sh | sh
```
Confirm Ollama is available:
```bash theme={null}
ollama list
```
### Step 2: Choose and pull a model tag
The default Ollama tag is `laguna-xs.2:latest`, which uses the same model blob as `laguna-xs.2:q4_K_M`. Use a different tag when you want higher precision and have enough memory.
| Tag | Approximate size | When to use it |
| ---------------------- | ---------------- | ----------------------------------------------------------- |
| `laguna-xs.2:latest` | 23 GB | Default. Recommended for most local setups. |
| `laguna-xs.2:q4_K_M` | 23 GB | Same as `:latest`. Cross-platform. |
| `laguna-xs.2:q8_0` | 37 GB | NVIDIA on Linux with comfortable VRAM. |
| `laguna-xs.2:bf16` | 67 GB | Full precision. Hopper, Blackwell, or 96 GB+ Apple Silicon. |
| `laguna-xs.2:nvfp4` | 22 GB | Apple Silicon only with the MLX backend. |
| `laguna-xs.2:mxfp8` | 36 GB | Apple Silicon only with the MLX backend. |
| `laguna-xs.2:mlx-bf16` | 67 GB | Apple Silicon only with the MLX backend. |
Pull the tag you want to run. For example, to pull the default tag, run:
```bash theme={null}
ollama pull laguna-xs.2:latest
```
### Step 3: Test the model in Ollama
You can chat with the model directly through Ollama to confirm it works. Use the same tag you pulled in the previous step:
```bash theme={null}
ollama run laguna-xs.2:latest
```
### Step 4: Install Poolside Agent CLI
Install Poolside Agent CLI so `pool` can connect to the model that Ollama serves locally:
```bash theme={null}
curl -fsSL https://downloads.poolside.ai/pool/install.sh | sh
```
Verify the installation:
```bash theme={null}
pool --version
```
The command prints the installed version. For installation details, see [Install Poolside Agent CLI](/cli/install).
### Step 5: Launch `pool` against the local model
Go to the project directory you want to work in, then point `pool` at the model Ollama serves on your machine. Use the same tag you used in step 2. This example uses `laguna-xs.2:latest`:
```bash theme={null}
cd
ollama launch pool --model laguna-xs.2:latest
```
When the session starts, send a prompt:
```text theme={null}
Summarize this project and suggest one small improvement.
```
You know the setup worked when the agent responds using the local Laguna XS.2 model.
## Optional: Work in your editor
Because `pool` supports ACP, you can connect the same local agent to any ACP-compatible editor instead of working from the terminal:
* [Use Poolside in Zed](/integrations/zed)
* [Use Poolside in JetBrains](/integrations/jetbrains)
* [Use Poolside in another ACP-compatible editor](/integrations/other-acp)
## Next steps
Keep working in the terminal with interactive sessions, automation, and other Poolside Agent CLI workflows.
Shape agent behavior and control what it can do.
## Related resources
* [Download the Laguna XS.2 model weights](https://huggingface.co/poolside/Laguna-XS.2)
* [Read how Poolside trained Laguna XS.2 in A Deeper Dive](https://poolside.ai/blog/laguna-a-deeper-dive)
* [Join the Poolside Discord](https://discord.com/invite/poolsideai) to give feedback, ask questions, and share what you build