gpt-oss:120b is a free open-weight OpenAI’s LLM-model with 120 billion parameters designed for powerful reasoning, agentic tasks and versatile developer use cases.

Server with gpt-oss:120b

Get gpt-oss:120b pre-installed on servers in the Netherlands, Finland, Germany, Iceland, Turkey, Poland, the USA, the UK, Spain, Switzerland and France.

Rent a virtual (VPS) or a dedicated server with pre-installed gpt-oss:120b - a free OpenAI LLM model with 120 billion parameters for powerful reasoning, agentic and coding tasks. Simply select gpt-oss:120b, configure your server and start working.

Already installed - we have taken care of all the technical aspects
Fine-tuned server - high performance configurations optimized for gpt-oss:120b
Supported 24/7 - we are always ready to help

4.3/5

4.8/5

SERVERS In action right now 5 000+

How it works

Choose server and license

Begin by choosing the most suitable server to meet your specific requirements. During the ordering process, choose gpt-oss:120b among the apps options, apply your network settings and set any other necessary parameters.
Place your order

After successfully placing your order and making the payment, our team will reach out to you with precise details about when your server will be ready for use. Typically, server setup takes no longer than 15 minutes, though the duration may vary depending on the type of server you choose.
Start working

Once your server is ready, we will promptly send you all the necessary access credentials via email. You can rest assured knowing that gpt-oss:120b will be pre-installed, enabling you to get to work without delay.

gpt-oss:120b on Dedicated H100

Rent a Dedicated Server with total out-of-band management in the Netherlands, Finland, Germany, Iceland, Turkey, Poland, the USA, the UK, Spain, Switzerland and France.

Server delivery ETA: ≈60 minutes.

gpt-oss:120b — officially free software

gpt-oss:120b is open‑weight and free. It is available under the Apache 2.0 license, allowing both commercial and private use for free.

We guarantee that our servers are running secure and original software.

FAQ

How to install gpt-oss:120b on a Virtual or Dedicated Server?

To install gpt-oss:120b, you simply need to select it while ordering a server on the HOSTKEY website. Our auto-deployment system will install it on your server for you.

I am having trouble installing and/or using gpt-oss:120b

If you have any difficulties or questions when installing and/or using this software, carefully review the documentation on the developer’s official website, read about typical problems and how to solve them or contact OpenAI support.

gpt-oss:120b key features

gpt-oss:120b is an open-weight language model by OpenAI, widely used for reasoning tasks, long-context applications and building custom AI agents or tools. It’s popular for its strong performance, openness (Apache 2.0 license), and ability to run on a single high-end GPU. Developers use it for cost-effective, private or domain-specific AI deployments.

Free and open‑weight

The model’s weights are publicly released under a permissive Apache 2.0 license, allowing commercial use, modification, and redistribution.

High performance

On reasoning, coding, competition math, health tasks etc., it matches or exceeds OpenAI’s own “o4‑mini” in many benchmarks, showing the effectiveness of its architecture.

MoE architecture

Although the total parameter count is ~117‑120B, only ~5.1B parameters are active per token thanks to Mixture‑of‑Experts (MoE) routing, which boosts efficiency.

Very long context window

It supports processing prompts + responses of up to 128K tokens, enabling the handling of very large documents, extended dialogues or lengthy chains of reasoning.

Efficient MXFP4 quantization

The weights (especially in the MoE layers) are quantized to formats like MXFP4, reducing memory footprint so the large model can run on a single ~80 GB GPU.

Configurable reasoning effort

Users can set “reasoning effort” to low, medium or high; this lets you trade off between speed (latency) and thoroughness / accuracy depending on the task.

High data security

With self-hosted gpt-oss:20b, all your data stays and is handled entirely on your own servers, so there is no processing that takes place outside your system or network.

Flexible deployment

Because of its efficiency tweaks (MoE, quantization), it can be run locally (on high‑end GPUs), so it’s built to be customizable, hostable “on‑premises” for enterprise/privacy use.

Strong reasoning

It handles chain‑of‑thought reasoning, supports function calls / tool integration (e.g. web search, code execution) and is fine‑tuned to follow instructions well.

Get pre-installed gpt-oss:120b

on servers located in data centers across Europe, the USA, and Turkey.

Why choose gpt-oss:120b at HOSTKEY?

TIER III Data Centers

Top reliability and security provide stable operation of your servers and 99.982% annual uptime.
DDoS protection

The service is organized using software and hardware solutions to protect against TCP-SYN Flood attacks (SYN, ACK, RST, FIN, PUSH).
Round-the-clock technical support

The application form allows you to get technical support at any time of the day or night. First response within 15 minutes.

What customers say

After launching another successful IP — HUNT: Showdown, a competitive first-person PvP bounty hunting game with heavy PvE elements, Crytek aimed to bring this amazing game for its end-users. We needed a hosting provider that can offer us high-performance servers with great network speed, latency, and 24/7 support.

Stefan Neykov Crytek

doXray has been using HOSTKEY for the development and the operation of our software solutions. Our applications require the use of GPU processing power. We have been using HOSTKEY for several years and we are very satisfied with the way they operate. New requirements are setup fast and support follows up after the installation process to check if everything is as requested. Support during operations is reliable and fast.

Wimdo Blaauboer doXray

We would like to thank HOSTKEY for providing us with high-quality hosting services for over 4 years. Ip-label has been able to conduct many of its more than 100 million daily measurements through HOSTKEY’s servers, making our meteorological coverage even more complete.

D. Jayes IP-Label

1 /

Our Ratings

4.3 out of 5

4.8 out of 5

4.0 out of 5

Hosting Control Panels VPN servers Databases Developer Tools Frameworks Business apps Virtualization Website & CMS Storage software Communication Monitoring Streaming software Kubernetes ispmanager cPanel CyberPanel FASTPANEL Personal Shadowsocks VPN Wireguard UI VPN MongoDB Docker Dokku Gitea Appwrite Proxmox VE VMware and RedHat's oVirt WordPress Rocket.Chat Owncast AzuraCast cPanel license Reseller hosting сPanel CyberPanel VPS Dedicated server with WordPress CyberPanel VPS CRM software Security software and VPN Jitsi Nextcloud LEMP MySQL Grafana KASM RabbitMQ OpenSearch N8N GitLab Minikube Moodle Hiddify Mastodon Drupal Rocket.Chat Ubuntu Rocket.Chat Docker Rocket.Chat Docker LAMP OpenCart TeamSpeak Mumble Palworld Joomla Odoo Games Minecraft: Java Edition Server Database Monitoring Kasm MicroK8s WooCommerce TrueNAS MinIO BigBlueButton Webmin Desktop Desktop Openlitespeed Prometheus Zabbix Machine Learning Self-hosted AI Chatbot PyTorch Xubuntu OpenPanel PyTorch Hestia Control Panel Node.js Django LinuxGSM + Web LGSM Jupyter Notebook JupyterLab Shopify Apache Spark Anaconda Magento Apache Guacamole + Xfce Apache Airflow Minecraft server the UK

Server with gpt-oss:120b

How it works

Choose server and license

Place your order

Start working