Install Ollama
Install Ollama on Windows, macOS, or Linux from the official download page at https://ollama.com/download. After installation, confirm the Ollama CLI is available on your PATH.
Text / Intermediate
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 9/24/2026
LOCALRENTED GPU
Before you begin
- Difficulty
- Intermediate
- Software
- Ollama, gpt-oss:20b
- Hardware
- For the publisher's 14.0 GB Ollama text package at a short 4K context, we estimate at least 22 GB GPU memory or 32 GB Apple unified memory. For a more comfortable starting point, use 32 GB GPU memory or 40 GB unified memory. These are capacity estimates, not speed tests; longer context and other apps need additional headroom.
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
View weight source gpt-oss · 20B · official
For the publisher's 14.0 GB Ollama text package at a short 4K context, we estimate at least 22 GB GPU memory or 32 GB Apple unified memory. For a more comfortable starting point, use 32 GB GPU memory or 40 GB unified memory. These are capacity estimates, not speed tests; longer context and other apps need additional headroom.
02
THE WORKFLOW
Set up gpt-oss · 20B on your machine
Pick your operating system. Every command below is for the selected package and runtime.
Install Ollama for this operating system before running the model command.
Download the gpt-oss-20b model package
Use Ollama to pull the exact published gpt-oss:20b package. This downloads the model files into your local Ollama store so it can run offline.
ollama pull gpt-oss:20bStart the model with Ollama
Launch the model in an interactive Ollama session. If the model was already pulled, this starts it immediately from local storage.
ollama run gpt-oss:20bSet a reasoning level for the session
In the Ollama prompt, set the reasoning level with a system instruction. Type the following as your first message: Reasoning: high Use low for fast general dialogue, medium for balanced speed and detail, or high for deep and detailed analysis. The model is trained on the Harmony response format and should be used with it; the Ollama integration handles this automatically.
Send a specific reasoning task
Paste the following prompt into the same Ollama session: A bat and a ball cost $1.10 in total. The bat costs $1.00 more than the ball. How much does the ball cost? Explain your reasoning step by step, then give the final answer.
Check the model output
Read the streamed reply. A correct reasoning response identifies the ball as $0.05 and shows the algebra: if the ball is x and the bat is x + 1.00, then x + (x + 1.00) = 1.10, so 2x = 0.10 and x = 0.05. The response should be structured according to the Harmony format that gpt-oss uses.
03
SUCCESS CHECK · gpt-oss · 20B
Check a known reasoning problem
Try a short multi-step problem with a known result. Verify the final answer and key steps independently before increasing context.
This is a source-linked setup, not a YouRunAI hardware test. Confirm your exact runtime version, package, and output before relying on it.
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
3 SOURCESSources and files
Original instructions, model files, and compatibility notes behind this setup.
The model behind this workflow
gpt-oss · 20BWill it run on your machine?
Save your machine to see a personalized rating and its reasoning.
Add my hardwareKeep exploring
Text
BeginnerSet up a private AI chat assistant
Install a local runtime, run Qwen3.5 9B, confirm responses, and know when to choose the smaller 4B package.
SOFTWAREOllama
Coding
IntermediateBuild a private local coding assistant
Connect an open coding-capable model in Ollama to Cline, run a small repository task, and review the result locally.
SOFTWAREOllama + Cline
Images
IntermediateGenerate images on your own GPU
Use the official FLUX.2 Klein 4B ComfyUI template with exact model files, a first prompt, and an output check.
SOFTWAREComfyUI