gpt-oss 20B

OpenAI's open-weight reasoning model with adjustable reasoning effort, in a ready-to-use chat UI.

Overview

gpt-oss-20b is a mixture-of-experts model released by OpenAI under Apache 2.0. Only ~3.6B parameters are active per token, so it is fast, and its native 4-bit weights fit in about 16 GB. This deployment gives you Open WebUI in the browser with Ollama behind it.

Key features

• ✓
  Adjustable reasoning effort
• ✓
  Tool use and structured outputs
• ✓
  ChatGPT-style web UI
• ✓
  Apache 2.0

Use cases

• →
  Private ChatGPT for a team
• →
  Agent prototyping
• →
  Offline / data-sensitive chat

On this template

Runs on the Open WebUI (Ollama) template, exposing its Open WebUI at a private HTTPS address. You also get root SSH and JupyterLab.

OLLAMA_PULL

gpt-oss:20b

Quick start

1. Click Deploy and pick an available GPU — only offers with enough VRAM are shown.
2. Wait for the status to turn running. The first start downloads the model, which can take a few minutes.
3. Use the connection details on your rental page:

Open https://r12-abcd1234-app.gpu.clearlayer.ca
Gateway login: user  edge   password  <app-token>
Then create your Open WebUI account (the first account is the admin).