# Can We Get WiCi Infer API use?

**URL:** <https://forums.realmacsoftware.com/t/can-we-get-wici-infer-api-use/58591>\
**Category:** API\
**Created:** [November 21, 2026, 2:48pm UTC](https://forums.realmacsoftware.com/t/can-we-get-wici-infer-api-use/58591 "2026-11-21T14:48:00Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![thominator](https://dub1.discourse-cdn.com/flex005/user_avatar/forums.realmacsoftware.com/thominator/32/35233_2.png) [@thominator](https://forums.realmacsoftware.com/u/thominator)\
**Post date:** [November 21, 2026, 2:48pm UTC](https://forums.realmacsoftware.com/t/can-we-get-wici-infer-api-use/58591/1 "2026-11-21T14:48:00Z")

</div>

Some of us have big machines with lots of memory. WiCi Infer now runs a 177B parameter model on my Studio with 90+ tokens/second. It has a Local API hook at 127.0.0.1:8080/v1. Can we get this linked up to run in the Elements API window?

---

<div class="post-metadata">

**Author:** ![thominator](https://dub1.discourse-cdn.com/flex005/user_avatar/forums.realmacsoftware.com/thominator/32/35233_2.png) [@thominator](https://forums.realmacsoftware.com/u/thominator)\
**Post date:** [November 21, 2026, 3:52pm UTC](https://forums.realmacsoftware.com/t/can-we-get-wici-infer-api-use/58591/2 "2026-11-21T15:52:40Z")

</div>

For those who might want to try the same thing, here’s the conversation to set it up via MCP and WiCi’s response (note that it took a bit longer to do this as I’ve got a lot of stuff running on this Studio right now and some spooling happened)🙂

 ![bythom-0683](https://europe1.discourse-cdn.com/flex005/uploads/realmacsoftware1/original/3X/7/d/7db598fe35ac15f3abd1fff40d1b1a0c65182321.webp)

---

<div class="post-metadata">

**Author:** ![thominator](https://dub1.discourse-cdn.com/flex005/user_avatar/forums.realmacsoftware.com/thominator/32/35233_2.png) [@thominator](https://forums.realmacsoftware.com/u/thominator)\
**Post date:** [November 21, 2026, 4:20pm UTC](https://forums.realmacsoftware.com/t/can-we-get-wici-infer-api-use/58591/3 "2026-11-21T16:20:58Z")

</div>

After a bit of memory cleanup and use, I’d say that the 177B/4-bit Qwen is running about one-tenth the speed of Claude on my Studio. Considering the huge model size, I find that respectable. It’s definitely workable. Most of the slowdown is inference (when it infers, it’s using the SSD).
