OpenAI · Reasoning Models

gpt-oss-120b

Name: gpt-oss-120b
Author: OpenAI

OpenAI's larger open-weight reasoning model: a 117B mixture-of-experts with 5.1B active parameters that fits on a single 80 GB GPU.

Official page

Run it locally

With Ollama installed, download and start the default version with:

ollama run gpt-oss:120b

Variant	Download
gpt-oss:120b	65GB

Memory: About 65GB for the default gpt-oss:120b version (4-bit)
Formats: Safetensors (Hugging Face), GGUF (Ollama, llama.cpp, LM Studio)

The download size is roughly the memory (RAM or GPU VRAM) needed to load a variant; allow extra for long contexts. See our hardware guide.

Overview

gpt-oss-120b was released in August 2025 together with gpt-oss-20b. OpenAI reported performance close to its o4-mini model on core reasoning benchmarks.

Highlights

117B total, 5.1B active parameters
Runs on a single 80 GB GPU
Adjustable reasoning effort and tool use
Apache 2.0 license

Typical uses

Self-hosted reasoning, coding and agent workloads.

Things to consider

Needs about 65 GB of memory locally.
Text only.
Download sizes refer to the default 4-bit quantized versions in the Ollama library; full-precision weights are larger.

Specifications are taken from the model card on Hugging Face, the Ollama library and the provider’s announcement. Benchmark results depend on evaluation settings; see how AI benchmarks work.

#Reasoning Models #Open Weights #Local AI #OpenAI