LLMs · OpenAI

gpt-oss 120B

Name: gpt-oss 120B
Author: OpenAI

Parameters: 117B (5.1B 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.

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

ollama run gpt-oss:120b

Quantized files · GGUF

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

huggingface.co/ggml-org/gpt-oss-120b-GGUF (opens in a new tab)

ollama run hf.co/ggml-org/gpt-oss-120b-GGUF

Original weights · Hugging Face

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

huggingface.co/openai/gpt-oss-120b (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 2 days ago against Hugging Face, Ollama and GitHub.

Apps that run gpt-oss 120B

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.

Mac (Apple silicon)

LM Studio

Runs the MLX build, typically 20–35% faster than GGUF for a model with 5.1B active parameters on Apple silicon.

Also good:

Windows PC, NVIDIA GPU

Ollama

One command with Ollama’s own build of this model.

Also good:

Windows PC, AMD Radeon

Lemonade

AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.

Also good:

Linux, NVIDIA GPU

Ollama

One command with Ollama’s own build of this model.

Also good:

Linux server, 80 GB+ GPUs

vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

Also good:

App	Type	Opens it as	Systems	Engine	Start
LM Studio	Desktop app	GGUF or MLX	macOSWindowsLinux	llama.cpp, MLX	Open in LM Studio
Ollama	CLI + API	Ollama library	macOSWindowsLinux	llama.cpp, MLX	`ollama run gpt-oss:120b`
llama.cpp	CLI + API	GGUF	macOSWindowsLinux	llama.cpp	`llama-server -hf ggml-org/gpt-oss-120b-GGUF:Q4_K_M`
Jan	Desktop app	GGUF or MLX	macOSWindowsLinux	llama.cpp, MLX	Open in Jan
MLX LM	CLI + API	MLX	macOS	MLX	`mlx_lm.chat --model lmstudio-community/gpt-oss-120b-MLX-8bit`
vLLM	Server	Original weights	WSLWindowsLinux	vLLM	`vllm serve openai/gpt-oss-120b`
SGLang	Server	Original weights	WSLWindowsLinux	SGLang	`python3 -m sglang.launch_server --model-path openai/gpt-oss-120b`
Docker Model Runner	CLI + API	GGUF	macOSWindowsLinux	llama.cpp, vLLM	`docker model run hf.co/ggml-org/gpt-oss-120b-GGUF:Q4_K_M`
Lemonade	Desktop app	GGUF	macOSWindowsLinux	llama.cpp, ONNX Runtime GenAI	`lemonade pull ggml-org/gpt-oss-120b-GGUF:Q4_K_M`
Unsloth Desktop	Desktop app	GGUF or MLX	macOSWindowsLinux	llama.cpp, MLX, stable-diffusion.cpp	Open in Unsloth Desktop
Atomic Chat	Desktop app	GGUF or MLX	macOSWindowsLinux	llama.cpp, MLX-VLM	Open in Atomic Chat
GhidrAssist	RE plugin	GGUF or MLX	macOSWindowsLinux	uses Ollama, LM Studio or any OpenAI-compatible server	Add it to Ghidra, then point it at a local model server
Gepetto	RE plugin	GGUF or MLX	macOSWindowsLinux	uses Ollama or an OpenAI-compatible server	Add it to IDA Pro, then point it at a local model server
BinAssist	RE plugin	GGUF or MLX	macOSWindowsLinux	uses Ollama, LM Studio or any OpenAI-compatible server	Add it to Binary Ninja, then point it at a local model server
r2ai and decai	RE plugin	GGUF or MLX	macOSWindowsLinux	uses Ollama, llama.cpp or LM Studio	Add it to radare2, then point it at a local model server
KoboldCpp	Desktop app	GGUF	macOSWindowsLinux	llama.cpp	Get KoboldCpp
Text Generation WebUI	Desktop app	GGUF	macOSWindowsLinux	llama.cpp, Transformers, ExLlamaV3	Get Text Generation WebUI
llamafile	CLI + API	GGUF	macOSWindowsLinux	llama.cpp	Get llamafile
Msty Studio	Desktop app	GGUF or MLX	macOSWindowsLinux	Ollama, llama.cpp, MLX	Open in Msty Studio
Llama (macOS)	Desktop app	GGUF	macOS	llama.cpp	Open in Llama (macOS)
RecurseChat	Desktop app	GGUF	macOS	llama.cpp	Open in RecurseChat
Inferencer	Desktop app	MLX	macOS	MLX	Get Inferencer
node-llama-cpp	Library	GGUF	macOSWindowsLinux	llama.cpp	Get node-llama-cpp
exo	Server	MLX	macOSLinux	MLX	Get exo
PocketPal AI	Mobile app	GGUF	iOSAndroid	llama.cpp	App Store Google Play
ChatterUI	Mobile app	GGUF	Android	llama.cpp	Download the APK
LLM Farm	Mobile app	GGUF	iOS	llama.cpp	Not on the App Store or TestFlight for now (checked 2026-11-09).

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory needed

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

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	66.6 GB	67.5 GB	68.5 GB	GGUF (opens in a new tab) Original weights (opens in a new tab)
`F16`	Full	234 GB	235 GB	235 GB	GGUF (opens in a new tab) Original weights (opens in a new tab)

Best hardware for gpt-oss 120B

The least expensive GPU in our catalog that runs it without offloading is the NVIDIA RTX PRO 6000 Blackwell (launch price $8,565) at MXFP4.

Quality	Hardware	Quant	Memory	Speed	Runs
84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	AMD Ryzen AI Max+ 395 (128 GB)	`MXFP4`	75.2 GB / 96.0 GB	47.7 tok/s	Runs great
84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	Apple M4 Max (128 GB)	`MXFP4`	75.2 GB / 96.0 GB	86.0 tok/s	Runs great
84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GB10 (128 GB)	`MXFP4`	76.7 GB / 115 GB	56.9 tok/s	Runs great
84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA RTX PRO 6000 Blackwell	`MXFP4`	72.3 GB / 96.0 GB	181 tok/s	Runs great
84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA RTX Spark N1X (6144-core GPU) (128 GB)	`MXFP4`	75.7 GB / 102 GB	61.3 tok/s	Runs great
84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.	Apple M2 Ultra (192 GB)	`MXFP4`	79.0 GB / 144 GB	111 tok/s	Runs great
84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	Apple M3 Ultra (256 GB)	`MXFP4`	82.9 GB / 192 GB	113 tok/s	Runs great
84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	Apple M3 Ultra (512 GB)	`MXFP4`	98.2 GB / 384 GB	113 tok/s	Runs great
84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	AMD Ryzen AI Max 385 (128 GB)	`MXFP4`	75.2 GB / 96.0 GB	47.7 tok/s	Runs great
84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	AMD Ryzen AI Max 390 (128 GB)	`MXFP4`	75.2 GB / 96.0 GB	47.7 tok/s	Runs great

Check it on your own hardware

Run it on a cluster

Devices that can’t run gpt-oss 120B alone can run it together. These example clusters do:

Try it with your own devices

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.