CodeText

Laguna

Models for agentic programming: they edit code in a repository on their own. The small XS runs on a Mac with 36 GB of memory; S 2.1 has a 1M-token context.

Developer
Poolside, USA
First release
Apr 2026
Latest release
Jul 2026
Sizes
33B-A3B – 225B-A23B
License
Commercial use allowedLaguna XS.2 and M.1: Apache 2.0; Laguna XS 2.1 and S 2.1: OpenMDW-1.1 (free commercial use)
Russian
Not stated
Ready-made builds
GGUF, AWQ, MLX (Apple)
Running
On your own serverNeeds a GPU
Industries
Software development
Deploy on your server Hugging Face

What it does

  • Coding agent for in-house development
  • Bug fixing and code improvements
  • Working with large codebases

Where it is used

IT departmentsSoftware developmentSystem integrators

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
no versions
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
fits

Versions

  1. Laguna S 2.1
  2. Laguna XS 2.1
  3. Laguna M.1
  4. Laguna XS.2

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can Laguna be used in a commercial project?

Yes. License: Laguna XS.2 and M.1: Apache 2.0; Laguna XS 2.1 and S 2.1: OpenMDW-1.1 (free commercial use). It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Laguna need?

At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Laguna support Russian?

The model card does not list languages, so Russian support cannot be promised — it has to be tested on your own examples.

Where can I download Laguna and what does it cost?

The Laguna weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

CodeQwen CoderAlibaba (Qwen team) · ChinaCommercial use allowed

The broadest open coding family: from 0.5B for autocompletion to 480B for agents. Qwen3-Coder-Next (80B, 3B active) works as a developer agent on a single GPU.

DetailsCodeDevstralMistral AI (with All Hands AI) · FranceCommercial use with conditions

Mistral models for agentic development: they read the repository, edit files and run commands on their own. The 24B version fits on a single GPU.

DetailsCodeKAT-Coder / KAT-DevKwaipilot (Kuaishou) · ChinaCommercial use allowed

Kuaishou models for agentic development, trained to solve real tasks in repositories. KAT-Coder-V2.5-Dev (35B, 3B active) is the open version of their closed flagship.

Details

Source: huggingface.co/poolside/Laguna-S-2.1. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.