Install Ollama
Install Ollama on your Windows, macOS, or Linux machine by following the instructions at https://ollama.com/download. This provides the `ollama` command-line tool used in the next steps.
Text / Intermediate
Set up private chat with gpt-oss · 120B
Run the gpt-oss 120B model locally through Ollama, send a first chat prompt, and confirm the model returns a response. This setup is intended for machines with enough memory or GPU capacity to host the 65 GB package; the model is a text-generation model in the gpt-oss series.
EstimatedSource checked 9/24/2026
LOCALRENTED GPU
Before you begin
- Difficulty
- Intermediate
- Software
- Ollama, gpt-oss:120b model
- Hardware
- For the publisher's 65.0 GB Ollama text package at a short 4K context, we estimate at least 88 GB GPU memory or 112 GB Apple unified memory. For a more comfortable starting point, use 120 GB GPU memory or 168 GB unified memory. These are capacity estimates, not speed tests; longer context and other apps need additional headroom.
TEXT / OLLAMASOURCE-LINKED SETUP
Set up private chat with gpt-oss · 120B, step by step.
Run the gpt-oss 120B model locally through Ollama, send a first chat prompt, and confirm the model returns a response. This setup is intended for machines with enough memory or GPU capacity to host the 65 GB package; the model is a text-generation model in the gpt-oss series.
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 · 120B · official
For the publisher's 65.0 GB Ollama text package at a short 4K context, we estimate at least 88 GB GPU memory or 112 GB Apple unified memory. For a more comfortable starting point, use 120 GB GPU memory or 168 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 · 120B 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 120B model
Pull the exact model package into your local Ollama library. The download is approximately 65 GB, so allow time for it to complete.
ollama pull gpt-oss:120bStart a local chat session with the model
Run the model to open an interactive chat in your terminal. This launches the model locally using Ollama.
ollama run gpt-oss:120bSend your first prompt
At the interactive prompt, type a question that requires a text answer, such as: `Explain why the sky is blue in two sentences.` Press Enter and wait for the model to generate a response.
Confirm the model responded
The chat session should display a generated text reply to your question. If you see a response from the model, the private local chat is working. You can continue typing additional prompts in the same session.
03
SUCCESS CHECK · gpt-oss · 120B
Check the first local reply
Ask a short question with a known answer. Confirm the selected local model responds and verify the answer yourself before using it for private work.
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 `ollama pull gpt-oss:120b` command fails or takes very long.
Check that you have enough free disk space (approximately 65 GB for the model) and a stable internet connection. If you are on a limited connection, consider using the smaller gpt-oss:20b variant instead by running `ollama run gpt-oss:20b`.
The model does not load or runs out of memory.
The 120B model is intended for a single 80 GB GPU or a machine with sufficient unified memory. If your hardware does not meet this, try the smaller `gpt-oss:20b` model or run the model on a machine with more memory.
The `ollama` command is not found after installation.
Restart your terminal or command prompt so the PATH is updated. On Linux, you may need to log out and back in or source your shell profile. Confirm the installation completed successfully from the Ollama download page.
REFERENCE LIBRARY
4 SOURCESSources and files
Original instructions, model files, and compatibility notes behind this setup.
The model behind this workflow
gpt-oss · 120BWill 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