Get the latest setups
Workflows/Run a private reasoning assistant with gpt-oss · 20B
Text / WORKFLOW

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.

EstimatedSource checked 9/29/2026
LOCALRENTED GPU
Freshness 17 out of 100. Repository age: 462 days old, Aug 4, 2025. Measures age, not quality.
Popularity 92 out of 100. 5,868,863 downloads in 30 days; 5,287 lifetime likes. Checked Nov 8, 2026. Measures adoption, not quality.
Arena Open Source Text: rank 110 of 228. Ranked model: gpt-oss-20b. Original model ranking, not a benchmark of this package. Export dated Nov 6, 2026. Source checked Nov 8, 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#110of 228 open models
gpt-oss-20bopenaiLicense: Apache 2.0

Original model ranking. This does not benchmark the selected quantization or package.

Export dated Nov 6, 2026Checked: Nov 8, 2026Overall board: #270
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 Nov 9, 2026. Statistics checked Nov 8, 2026. Statistics are marked for refresh after 72 hours.Full scoring method

Before you begin

Hardware

Estimates for the 14.0 GB Ollama package at 4K text context. A full GPU load needs room beyond the weight download for runtime and KV cache; CPU offload can run on smaller GPUs with enough system RAM, but responds more slowly.

Machinegpt-oss · 20B
NVIDIA GPU · 8 GBUse CPU offload with 32 GB RAM; slow.
NVIDIA GPU · 12 GBUse CPU offload with 32 GB RAM; slow.
NVIDIA GPU · 16 GBRuns at 4K text context; limited headroom.
NVIDIA GPU · 24 GBRuns at 4K with headroom; speed not tested.
NVIDIA GPU · 32 GBRuns at 4K with headroom; speed not tested.
AMD Radeon · 8 GBUse CPU offload with 32 GB RAM; slow. Confirm the Ollama GPU backend with ollama ps.
AMD Radeon · 16 GBRuns at 4K text context; limited headroom. Confirm the Ollama GPU backend with ollama ps.
AMD Radeon · 24 GBRuns at 4K with headroom; speed not tested. Confirm the Ollama GPU backend with ollama ps.
AMD Radeon · 32 GBRuns at 4K with headroom; speed not tested. Confirm the Ollama GPU backend with ollama ps.
Intel Arc · 8 GBUse CPU offload with 32 GB RAM; slow. Confirm the Ollama GPU backend with ollama ps.
Intel Arc · 16 GBRuns at 4K text context; limited headroom. Confirm the Ollama GPU backend with ollama ps.
Intel Arc · 24 GBRuns at 4K with headroom; speed not tested. Confirm the Ollama GPU backend with ollama ps.
Intel Arc · 32 GBRuns at 4K with headroom; speed not tested. Confirm the Ollama GPU backend with ollama ps.
Apple Silicon · 16 GB unifiedNeeds more unified memory at 4K; use a 24 GB Mac or lower-memory model.
Apple Silicon · 24 GB unifiedRuns at 4K text context; limited memory headroom.
Apple Silicon · 32 GB unifiedRuns at 4K text context with room to raise context; speed not tested.
Apple Silicon · 64 GB unifiedRuns at 4K text context with room to raise context; speed not tested.
CPU-only · 16 GB RAMBelow the 32 GB system-RAM starting point; choose a smaller model.
CPU-only · 32 GB RAMCan run in system RAM at 4K; expect slower replies than GPU.
CPU-only · 64 GB RAMCan run in system RAM at 4K; expect slower replies than GPU.

These are memory-fit starting points, not performance tests. Check the exact AMD or Intel Ollama backend and use ollama ps to see the GPU/CPU split; longer context or image input needs more memory.

TEXT / OLLAMASOURCE-LINKED SETUP

Run a private reasoning assistant with gpt-oss · 20B, step by step.

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.

Choose a package Run its commands Check the result
01
BEFORE YOU BEGIN

The documented package

This setup uses the package documented for this task. Review its source and supported platforms before starting.

Save your machine in My Hardware to get an automatic starting choice. You can always choose any package yourself.

CURRENT SETUP

gpt-oss · 20B · official

The 14.0 GB published Ollama download is smaller than total runtime memory. Start with 4K text context. 16 GB GPU memory or 24 GB unified Mac memory is an estimated full-load starting point; 24 GB GPU or 32 GB Mac leaves more headroom. Longer context and other apps increase memory use; check ollama ps for actual offload.

Freshness 17 out of 100. Repository age: 462 days old, Aug 4, 2025. Measures age, not quality.
Popularity 92 out of 100. 5,868,863 downloads in 30 days; 5,287 lifetime likes. Checked Nov 8, 2026. Measures adoption, not quality.
Arena Open Source Text: rank 110 of 228. Ranked model: gpt-oss-20b. Original model ranking, not a benchmark of this package. Export dated Nov 6, 2026. Source checked Nov 8, 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#110of 228 open models
gpt-oss-20bopenaiLicense: Apache 2.0

Original model ranking. This does not benchmark the selected quantization or package.

Export dated Nov 6, 2026Checked: Nov 8, 2026Overall board: #270
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 Nov 9, 2026. Statistics checked Nov 8, 2026. Statistics are marked for refresh after 72 hours.Full scoring method
View weight source
02
THE WORKFLOW

Set up gpt-oss · 20B on your machine

Choose where you want to run it. The instructions below update to match your selection.

CHOOSE YOUR SETUPMac

Use Terminal on Apple Silicon. Ollama for macOS is available from the official download page.

01

Install Ollama for macOS

Download the Mac application from Ollama, move it to Applications, and open it so the local service starts.

Download Ollama for Mac
02

Check Ollama in Terminal

Open a new Terminal window and confirm the command-line tool is available.

ollama --version
03

Download and start this exact package

Run the publisher-listed command. The first launch downloads the selected weights; subsequent launches reuse the local copy.

ollama run gpt-oss:20b
04

Solve and verify one reasoning task

At the Ollama chat prompt, paste: “A car travels 150 km in 2.5 hours at a steady speed. How far does it travel in four hours? Show the calculation.” The correct result is 240 km: 150 ÷ 2.5 = 60 km/h, then 60 × 4 = 240 km. This checks the actual selected model, not just that its download completed.

05

Confirm the local package

In a second Terminal window, verify that the selected package is installed locally.

ollama list
03
SUCCESS CHECK · gpt-oss · 20B

Check the worked answer

Run the exact prompt in the operating-system instructions. The correct result is 240 km: 150 ÷ 2.5 = 60 km/h, then 60 × 4 = 240 km. Confirm that Ollama lists the selected package and use ollama ps to check whether it ran on GPU or fell back to CPU.

This is a source-linked setup, not a YouRunAI hardware test. Confirm your exact runtime version, package, and output before relying on it.

Back to setup steps

When it doesn’t go to plan

The model answers incorrectly or ignores the Harmony format.

Start a fresh Ollama session with `ollama run gpt-oss:20b` and include the system instruction exactly as `Reasoning: high` before sending your task. gpt-oss models should only be used with the Harmony response format, which the Ollama integration applies when using the documented gpt-oss:20b package.

The pull fails or the model is not found.

Verify the exact package name `gpt-oss:20b` and that Ollama is installed and up to date from https://ollama.com/download, then rerun `ollama pull gpt-oss:20b`.

There is not enough memory or disk space to run the model.

Confirm at least 14 GB of free disk space for the Ollama gpt-oss:20b package and enough system memory for a 21B-parameter MoE model. Close other memory-intensive applications before running `ollama run gpt-oss:20b`.

REFERENCE LIBRARY

Sources and files

Original instructions, model files, and compatibility notes behind this setup.

4 SOURCES
01Publisher run instructionshuggingface.co02Official Ollama downloadollama.com03Ollama CLI referencedocs.ollama.com04Ollama GPU and driver supportdocs.ollama.com

The model behind this workflow

gpt-oss · 20B

Keep exploring

Text
SETUP GUIDE

Qwen3.5 · 9B private chat setup

Source-backed package and platform-route plan for private local chat with Qwen3.5 · 9B. Preserves the official Ollama 9B package, a smaller 4B family fallback, and a clearly labeled community uncensored GGUF option.

Freshness 37 out of 100. Release age: 255 days old, Feb 27, 2026. Measures age, not quality.
Popularity 91 out of 100. 6,335,106 downloads in 30 days; 2,331 lifetime likes. Checked Nov 8, 2026. Measures adoption, not quality.
SOFTWAREOllama
LOCALRENTED GPU
Estimated
Coding
SETUP GUIDE

Build a private coding assistant with Qwen3.8 27B

Run Qwen3.8 27B with Ollama, connect it to Cline in VS Code, and make one reviewable code change in a tiny local project.

Freshness 69 out of 100. Repository age: 96 days old, Aug 5, 2026. Measures age, not quality.
Popularity 96 out of 100. 7,668,187 downloads in 30 days; 19,373 lifetime likes. Checked Nov 8, 2026. Measures adoption, not quality.
Arena Open Source Web coding: rank 12 of 62. Ranked model: Qwen3.8-27B. Original model ranking, not a benchmark of this package. Export dated Nov 6, 2026. Source checked Nov 8, 2026. Human preference ranking, not hardware suitability.+3
SOFTWAREOllama + Visual Studio Code + Cline + Python
LOCALRENTED GPU
Estimated
Images
SETUP GUIDE

Create images locally with FLUX.2 Klein

Generate images from text prompts in ComfyUI with the fast distilled or more adjustable base 4B model. Save your results and reuse the visual workflow.

Freshness 32 out of 100. Release age: 298 days old, Jan 15, 2026. Measures age, not quality.
Popularity 77 out of 100. 436,763 downloads in 30 days; 1,098 lifetime likes. Checked Nov 8, 2026. Measures adoption, not quality.
SOFTWAREComfyUI
LOCALRENTED GPU
Verified source
Run a private reasoning assistant with gpt-oss · 20B | YouRunAI