Skip to main content

Dev Station Technology

AI Development

LightGBM development services for models on tabular data

We have no published LightGBM build. Our Python 3.13 back ends hold the records such a model learns from, and we say plainly that none of them trains one.

0Published builds on LightGBM
4.7.0Latest release, 18 Jul 2026
4.6.0Released 15 February
1GitHub org move, Microsoft to lightgbm-org
What we build

What we would take on with LightGBM

Models on records

Gradient boosting on tables such as inspection and fleet data.

Models behind an API

A FastAPI service in front of a trained model.

Evidence beside the score

A prediction that shows what drove it.

Upgrades

Moves onto 4.7.

Architecture

Where LightGBM would sit

A boosted model on the fleet data
Data
PostgreSQL and PostGISStops, legs, geofences
MQTT telematicsPosition and engine data
Model
LightGBM logo
LightGBM modelWhere it would sit
Python logo
FastAPIPython 3.13
Use
React logo
Dispatch consoleSixteen live screens

Illustration. A dashed outline marks where the technology would sit. We have no published build on it.

Releases

Recent LightGBM releases

The latest LightGBM releases
25 July

LightGBM 4.5.0

A minor release.

15 February

LightGBM 4.6.0

The next minor release.

18 July 2026

LightGBM 4.7.0

Marked latest. The notes say the project moved GitHub orgs from Microsoft to lightgbm-org.

Source: LightGBM releases on GitHub, checked 6 November 2026. The list shows day and month, and the asset timestamps give 2026 for 4.7.0.

Builds

The closest builds we can show you

TruckFleet Labs dispatch console and driver app built by Dev Station
Logistics, fleet operations

TruckFleet Labs

Stops, legs and telematics in PostGIS and Redis, the data a boosted model would learn from.

112 to 97 kmOne route after route sequencing
Sales OS account research product built by Dev Station
AI product, in-house

Sales OS

A graded brief with six scored axes, where every score carries its evidence.

1 creditOpens all six tabs of an account brief
Fit check

When LightGBM is the right call

Pick LightGBM when

  • Your data is a table with many rows
  • Training speed matters
  • You can explain the result to a user

Look elsewhere when

  • You need a published LightGBM build to inspect, which we do not have
  • The job is images or text, where deep learning fits
  • You have too few labelled rows
Stack

What LightGBM usually sits beside

XGBoost logoXGBoost
CatBoost logoCatBoost
scikit-learn logoscikit-learn
Python logoPython
Apache Airflow logoApache Airflow
Docker logoDocker
FAQs

What buyers ask first

Which LightGBM version is current?

LightGBM 4.7.0, marked latest on GitHub and released on 18 July 2026. Version 4.6.0 came out on 15 February.

Do you have a published LightGBM build?

No. We say so on the first call and show the nearest work, which is Python data builds with PostGIS and a sync queue.

Has the LightGBM repository moved?

Yes. The 4.7.0 release notes say the project changed GitHub orgs from Microsoft to lightgbm-org.

Who owns the code and the cloud accounts?

You do, from the first commit. Repositories and cloud accounts stay in your name.

Tell us what your table has to predict

Thirty minutes on your data, your labels and your LightGBM version. No sales pitch.

Let's Talk