Reasoning
How to deploy gpt-oss-120b on a GPU cloud
A 117B (MoE) reasoning model whose MXFP4 weights fit a single 80GB GPU. Full specs, license and use cases.
gpt-oss-120b size and hardware requirements
116.8B
Total parameters
Mixture-of-experts: 4 of 128 experts active per token (5.1B active parameters, stated on the model card)
Active parameters
MXFP4
Published precision
80.0 GB
Min VRAM (native)
| Precision | Weight size on disk | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| MXFP4 (native) | 60.8 GB | 80.0 GB | A100 | 1 | $0.851/hr |
How to run gpt-oss-120b
Run gpt-oss-120b with vLLM
From openai/gpt-oss-120b's own model card (requires vllm>=0.10.1+gptoss).
vllm serve openai/gpt-oss-120bSource: https://huggingface.co/openai/gpt-oss-120b/raw/main/README.md
Run gpt-oss-120b with Ollama
From the model card's own Ollama instructions; verified against Ollama's own library listing.
ollama run gpt-oss:120bRun gpt-oss-120b with GGUF quantizations
Prebuilt GGUF weights published at unsloth/gpt-oss-120b-GGUF. Run with llama.cpp's llama-server or load the repo directly in LM Studio.
llama-server -hf unsloth/gpt-oss-120b-GGUFDeploy gpt-oss-120b on Aquanode
Aquanode has no one-click deploy template for gpt-oss-120b; you install the inference engine yourself with the commands below. Aquanode sells GPU pods billed per second, not a hosted inference API.
- Launch a bare GPU pod sized to the requirement above (1× A100 or larger).
- Open a terminal on the pod, or save one of the commands above as a startup script so it runs automatically the first time the pod boots.
- Run the command and connect to the resulting endpoint.
Launch a GPU pod