​
Run GPT‑OSS 120B on Thunder Compute

Looking for the cheapest way to self‑host GPT‑OSS 120B or just want to try it out without buying hardware? Thunder Compute lets you spin up pay‑per‑minute NVIDIA A100 GPUs, so you only pay for what you use. Follow the steps below to get the model running in minutes.
Prerequisite: Ensure your Thunder Compute account is ready. If not, start with our Quickstart Guide.

​
Step 1 — Create a Cost‑Effective Prototyping‑Mode GPU Instance

Launch an 80 GB A100 instance (large enough to host the full 120 B model): 
tnr create \
  --gpu a100xl \
  --vcpus 4 \
  --mode prototyping \
  --disk-size-gb 200 \
  --template "ollama"
This command starts a lower‑cost prototyping‑mode instance with:
  • GPU: A100 80 GB
  • vCPUs: 4
  • Storage: 200 GB (from the Ollama template)
The GPU, vCPU Count, and Mode (Prototyping / Production), can be changed later if your requirements change, and the amount of storage can be increased if needed.
For details on templates, see the Instance Templates guide.

​
Step 2 — Check Status and Connect

Verify that the instance is running, it can take a minute to spin up: 
tnr status
Instance status output Connect to the instance: 
tnr connect <instance‑id>

​
Step 3 — Start Ollama and Download the Model

Inside the instance, start Ollama (this also launches OpenWebUI and a Cloudflare tunnel): 
start-ollama
While the UI is initializing, download the model, here we are downloading the 120B variant of GPT‑OSS, but any models can be downloaded from the Ollama Model Library: 
ollama pull gpt-oss:120b
Tip: If you encounter issues, consult the troubleshooting guide.
Give the UI about 60 seconds to finish loading. Ollama status output

​
Step 4 — Access the Web UI and Select the Model

  1. Open http://localhost:8080 in your browser.
  2. Choose gpt-oss:120b from the model dropdown.
OpenWebUI model selection

​
Step 5 — Run GPT‑OSS 120B

Enter a prompt in the web interface, for example:
“Tell a tale of a seaman who found the treasure of the clouds by following the sound of thunder.”

​
Conclusion

That’s it—the cheapest way to run GPT‑OSS 120B on Thunder Compute. For more, check out: Happy building!