# DGX Spark Owners: Anyone Successfully Connected Ollama to Cursor?

**URL:** <https://forum.cursor.com/t/dgx-spark-owners-anyone-successfully-connected-ollama-to-cursor/161258>\
**Category:** Help\
**Tags:** byok\
**Created:** [May 21, 2026, 7:39pm UTC](https://forum.cursor.com/t/dgx-spark-owners-anyone-successfully-connected-ollama-to-cursor/161258 "2026-05-21T19:39:07Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![alexus](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/alexus/32/82018_2.png) [@alexus](https://forum.cursor.com/u/alexus)\
**Post date:** [May 21, 2026, 7:39pm UTC](https://forum.cursor.com/t/dgx-spark-owners-anyone-successfully-connected-ollama-to-cursor/161258/1 "2026-05-21T19:39:07Z")

</div>

Hello World! 😉

I’m trying to figure out how to connect NVIDIA DGX Spark’s Ollama instance with Cursor. I already have Ollama running and can successfully access it over the network using `curl`, but I’m having trouble figuring out how to properly connect it to Cursor.

Any guidance would be greatly appreciated. Thanks!

---

<div class="post-metadata">

**Author:** ![deanrie](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/deanrie/32/1263_2.png) [@deanrie](https://forum.cursor.com/u/deanrie)\
**Post date:** [May 24, 2026, 7:52am UTC](https://forum.cursor.com/t/dgx-spark-owners-anyone-successfully-connected-ollama-to-cursor/161258/5 "2026-05-24T07:52:47Z")

</div>

Hey, you can’t connect to Ollama directly over LAN. In Cursor, Override OpenAI Base URL needs a public HTTPS endpoint because requests still go through our servers, prompt building, context, Tab, and Agent run on our side.

Workaround: expose your local Ollama through a tunnel like [https://ngrok.com/](https://ngrok.com/) or [Cloudflare Tunnel · Cloudflare One docs](https://developers.cloudflare.com/cloudflare-one/connections/connect-networks/), get a public HTTPS URL, then paste it into `Settings > Models > Override OpenAI Base URL`. Then add a custom model name and enable an OpenAI API Key, for Ollama a dummy key is fine.

More details and discussion are in this thread: [How can I use a local LLM on my desktop/AI computer?](https://forum.cursor.com/t/how-can-i-use-a-local-llm-on-my-desktop-ai-computer/152419)

If you hit a model name validation error when adding the model, like `llama3.1:latest` not being accepted, try naming the model in Ollama so it matches one of Cursor’s known model names, for example `gpt-4o`. That’s a known quirk. There’s no ETA yet for native support for local models without a tunnel.

---

<div class="post-metadata">

**Author:** ![alexus](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/alexus/32/82018_2.png) [@alexus](https://forum.cursor.com/u/alexus)\
**Post date:** [May 24, 2026, 2:23pm UTC](https://forum.cursor.com/t/dgx-spark-owners-anyone-successfully-connected-ollama-to-cursor/161258/6 "2026-05-24T14:23:29Z")

</div>

I appreciate your reply, thank you very much!

the missing piece of the puzzle for me was..  
.. one have to _expand_ “API Keys” link to see “Override OpenAI Base URL”, etc

Thanks again!

---

<div class="post-metadata">

**Author:** ![system](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/system/32/99069_2.png) [@system](https://forum.cursor.com/u/system)\
**Post date:** [June 20, 2026, 7:39pm UTC](https://forum.cursor.com/t/dgx-spark-owners-anyone-successfully-connected-ollama-to-cursor/161258/7 "2026-06-20T19:39:33Z")

</div>

This topic was automatically closed after 30 days. New replies are no longer allowed.