# @alican.kiraz0 on Instagram

- **Type:** Image
- **Original URL:** https://www.instagram.com/p/DWV6vcxDAvi
- **Gondola URL:** https://gondola.cc/posts/63335499-alicankiraz0-instagram
- **Thumbnail:** https://img.gondola.cc/tr:w-,h-,fo-auto/postThumbnails/1c451d46d1.jpg
- **Posted:** 2026-03-26T09:24:44.000+00:00
- **Account Owner:** Alican Kiraz (@alican.kiraz0) — https://gondola.cc/alican.kiraz0

## Caption

Mom, I finally changed the world, even if only a little… 🥹❤️

Guys, presenting the World’s First Heterogeneous nvidia CUDA + apple Metal Distributed Inference Cluster 🎉

I managed to get Nvidia CUDA + Apple Metal running distributed LLM inference together — same pipeline, same ring. I owe this to exo’s amazing infrastructure. ❤️

The BF16 model splits across architectures — layers 0-10 on NVIDIA, layers 10-32 on Apple Silicon.

I achieved this by adding just ~200 lines across 5 files to exo’s brilliant open-source codebase.

PR to exolabs coming soon.

#exolab #nvidia #macmini #apple #ai

## Stats

- **Views:** 0
- **Likes:** 396
- **Shares:** 0
- **Comments:** 0

## Tags

macmini, exolab, apple, ai, nvidia

---
Copyright (c) Gondola