LLMs · OpenAI

gpt-oss 20B

Name: gpt-oss 20B
Author: OpenAI

Parameters: 21B (3.6B active)
Architecture: Mixture of experts
Max context: 128K tokens
License: apache-2.0
Released: 2025-08

How to run it

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

ollama run gpt-oss:20b

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/ggml-org/gpt-oss-20b-GGUF (opens in a new tab)

ollama run hf.co/ggml-org/gpt-oss-20b-GGUF

Original weights · Hugging Face

Full-precision files from OpenAI, for fine-tuning, vLLM, Transformers.

huggingface.co/openai/gpt-oss-20b (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from OpenAI. The weights themselves download from Hugging Face.

github.com/openai/gpt-oss (opens in a new tab)

git clone https://github.com/openai/gpt-oss

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.

KV cache: alternating full and 128-token sliding-window layers: the KV estimate counts the full layers plus a small allowance.

Quantization	Quality	Weights	Total at 8K context	Total at 32K context	Download
`MXFP4`	Native	11.9 GB	12.7 GB	13.4 GB	GGUF (opens in a new tab) Original weights (opens in a new tab)
`F16`	Full	41.8 GB	42.6 GB	43.3 GB	GGUF (opens in a new tab) Original weights (opens in a new tab)

Best hardware for gpt-oss 20B

The least expensive GPU in our catalog that runs it without offloading is the AMD Radeon RX 7600 XT (launch price $329) at MXFP4.

Grade · points	Hardware	Quant	Memory	Speed	Fit
86 ptsExcellent (S) · 86 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	AMD Radeon RX 9070 XT	`MXFP4`	13.5 GB / 16.0 GB	101 tok/s	Runs well
86 ptsExcellent (S) · 86 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	NVIDIA GeForce RTX 4060 Ti 16GB	`MXFP4`	13.5 GB / 16.0 GB	52.5 tok/s	Runs well
86 ptsExcellent (S) · 86 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	NVIDIA GeForce RTX 4070 Ti SUPER	`MXFP4`	13.5 GB / 16.0 GB	123 tok/s	Runs well
86 ptsExcellent (S) · 86 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	NVIDIA GeForce RTX 4080 SUPER	`MXFP4`	13.5 GB / 16.0 GB	134 tok/s	Runs well
86 ptsExcellent (S) · 86 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	NVIDIA GeForce RTX 5060 Ti 16GB	`MXFP4`	13.5 GB / 16.0 GB	81.7 tok/s	Runs well
86 ptsExcellent (S) · 86 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	NVIDIA GeForce RTX 5070 Ti	`MXFP4`	13.5 GB / 16.0 GB	163 tok/s	Runs well
86 ptsExcellent (S) · 86 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	NVIDIA GeForce RTX 5080	`MXFP4`	13.5 GB / 16.0 GB	175 tok/s	Runs well
85 ptsExcellent (S) · 85 of 100 points: Model quality 31.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	Apple M4 Pro (24 GB)	`MXFP4`	14.0 GB / 16.1 GB	42.9 tok/s	Tight fit
84 ptsGreat (A) · 84 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.4/15	AMD Radeon RX 7900 XTX	`MXFP4`	13.9 GB / 24.0 GB	151 tok/s	Runs well
84 ptsGreat (A) · 84 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.4/15	NVIDIA GeForce RTX 3090	`MXFP4`	13.9 GB / 24.0 GB	171 tok/s	Runs well

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.