Agents / OpenAI

gpt-oss · 20B

An open-weight reasoning and tool-use model with a publisher-documented Ollama path for consumer hardware.

Verified sourceSource checked 9/23/2026

LOCALRENTED GPUOPEN WEIGHTS

Freshness 19 out of 100. Repository age: 437 days old, Aug 4, 2025. Measures age, not quality.

Popularity 92 out of 100. 5,988,822 downloads in 30 days; 5,180 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.

Arena Open Source Text: rank 107 of 225. Ranked model: gpt-oss-20b. Export dated Oct 13, 2026. Source checked Oct 15, 2026. Human preference ranking, not hardware suitability.

Category rankings & sources

Each position belongs to a separate Arena category. These are human preference rankings—not hardware recommendations. We do not combine the categories into one score.

Text#107of 225 open models

gpt-oss-20bopenaiLicense: Apache 2.0

Export dated Oct 13, 2026Checked: Oct 15, 2026Overall board: #266

View official Text board

Rankings reflect the dated export; live Arena boards can change. Open-source positions use Arena’s open-model filter. The overall position also includes the other models on that category board. Availability of weights and license terms still need to be checked separately.

What do these scores mean?

Two ways to compare models. Neither score measures answer quality, benchmark performance, or whether a model fits your machine.

Freshness · release age

A new release starts at 100. The score halves every 180 days: 100 × 2^(−age in days / 180). When the release date is unavailable, a repository date is a fallback—not proof of when the model was released. Missing dates stay unscored.

Check the date source

Popularity · adoption

Downloads over the past 30 days carry 80% of the score; lifetime likes carry 20%. Both use a logarithmic scale, capped at 10 million downloads and 100,000 likes. If likes are unavailable, downloads carry all the weight. Missing download statistics stay unscored.

round(80 × min(1, log10(1 + downloads) / 7) + 20 × min(1, log10(1 + likes) / 5))

Check the statistics source

Scores as of Oct 15, 2026. Statistics checked Oct 15, 2026. Statistics are marked for refresh after 72 hours.Full scoring method

WORKFLOWS FOR THIS MODEL 3

What do you want to do?

Choose a task. Get the software, files, settings, and steps to run it.

MAKE IT PERSONALChoose your hardware

Private chat

Set up private chat with gpt-oss · 20B

Install Ollama, pull the gpt-oss:20b model, launch a local private chat session, send a first prompt, and verify the model responds.

Freshness 19 out of 100. Repository age: 437 days old, Aug 4, 2025. Measures age, not quality.

Arena Open Source Text: rank 107 of 225. Ranked model: gpt-oss-20b. Original model ranking, not a benchmark of this package. Export dated Oct 13, 2026. Source checked Oct 15, 2026. Human preference ranking, not hardware suitability.

Ollamagpt-oss:20b

1 packagemacOS / Windows / Linux

Open chat guide

Text

Extract structured data locally with gpt-oss 20B

Extract and validate a sample receipt with gpt-oss 20B through local Ollama and Python.

Freshness 19 out of 100. Repository age: 437 days old, Aug 4, 2025. Measures age, not quality.

OllamaPydantic

1 packagemacOS / Windows / Linux

Open setup guide

Reasoning

Run a private reasoning assistant with gpt-oss · 20B

Install Ollama, pull and run gpt-oss:20b locally, set a reasoning level, and verify a reasoning response from the model. This uses the publisher-documented Ollama path for the gpt-oss-20b open-weight model, which requires the Harmony response format and supports configurable low, medium, and high reasoning effort.

Freshness 19 out of 100. Repository age: 437 days old, Aug 4, 2025. Measures age, not quality.

Ollamagpt-oss:20b

1 packagemacOS / Windows / Linux

Open reasoning guide

Open a guide for its software, hardware requirements, and setup steps.

At a glance

Parameters: 21B total · 3.6B active
Architecture: Mixture of experts
License: Apache 2.0
Disk space: 14 GB
Software: Ollama, vLLM, Transformers

MY HARDWARE

Will it run on your machine?

Save your machine to see a personalized rating and its reasoning.

Add my hardware

Best for

Run local reasoning with adjustable effort.
Build a private structured-data extraction or tool-use process.

Tradeoffs

Use a runtime that handles the model’s Harmony format; direct raw prompting can behave incorrectly.
The 14 GB package size does not include all runtime and context memory.

Ways to run it

Ollama · Windows, macOS, Linux

The publisher documents this command; Ollama lists a 14 GB package. It uses the model’s Harmony format.

ollama run gpt-oss:20b

Official instructions

vLLM · Linux

vllm serve openai/gpt-oss-20b

Official instructions

Explore its uses

REASONINGAGENTSTOOLSSTRUCTURED OUTPUT

REFERENCE LIBRARY

Sources and files

Primary sources and files behind this model page.

2 SOURCES

01Publisher model card and Ollama commandshuggingface.co 02Ollama package sizeollama.com

Keep exploring

Agents

Z.ai

GLM 5.3

Explore 2 versions of GLM 5.3. Compare model sizes, packages, hardware requirements, and available setups.

2 versionsCompare sizes & formats

Kimi K3

An open-weight multimodal model for long-running coding, reasoning, and knowledge work.

Freshness 62 out of 100. Repository age: 124 days old, Jun 13, 2026. Measures age, not quality.

Arena Open Source Agents: rank 7 of 18. Ranked model: Kimi K3 (Max). Export dated Oct 14, 2026. Source checked Oct 15, 2026. Human preference ranking, not hardware suitability.+2

MODEL SIZE2.8T total · 104B active

LOCALRENTED GPU

Repository opened Jun 13, 2026

Agents

Google DeepMind

Gemma 4

Explore 4 versions of Gemma 4. Compare model sizes, packages, hardware requirements, and available setups.

4 versionsCompare sizes & formats

LOCALRENTED GPU

Compare versions →