# \#lemonade
**URL:** https://devcommunity.amd.com/tag/lemonade/159.md
[Latest](https://devcommunity.amd.com/latest.md) · [Categories](https://devcommunity.amd.com/categories.md) · [Tags](https://devcommunity.amd.com/tags.md)
---
## [Your PC can already run its wwn AI server - it just needs Lemonade](https://devcommunity.amd.com/t/your-pc-can-already-run-its-wwn-ai-server-it-just-needs-lemonade/1275)
**Author:** [@nirth\_AMD](https://devcommunity.amd.com/u/nirth_AMD)\
**Replies:** 0\
**Last updated:** [October 30, 2026, 11:39am UTC](https://devcommunity.amd.com/t/your-pc-can-already-run-its-wwn-ai-server-it-just-needs-lemonade/1275 "2026-10-30T11:39:20Z")
You find a cool AI app, open the settings, and it wants an OpenAI API key. So you either hand over a credit card and your data, or you go hunting through forum threads for some way to point it at a local model instead - …
---
## [Local Quantization and Multi-Backend Deployment with AMD Quark on Strix Halo](https://devcommunity.amd.com/t/local-quantization-and-multi-backend-deployment-with-amd-quark-on-strix-halo/1257)
**Author:** [@nirth\_AMD](https://devcommunity.amd.com/u/nirth_AMD)\
**Replies:** 0\
**Last updated:** [October 26, 2026, 2:55pm UTC](https://devcommunity.amd.com/t/local-quantization-and-multi-backend-deployment-with-amd-quark-on-strix-halo/1257 "2026-10-26T14:55:26Z")
Local Quantization and Multi-Backend Deployment with AMD Quark on Strix Halo - Quantize a 35B MoE model in-place and run it on three backends without leaving your workstation What’s in it: This walkthrough takes a Qw…
---
## [Building Your First Agent with GAIA - Stop Guessing. Ask Your GPU](https://devcommunity.amd.com/t/building-your-first-agent-with-gaia-stop-guessing-ask-your-gpu/1130)
**Author:** [@nirth\_AMD](https://devcommunity.amd.com/u/nirth_AMD)\
**Replies:** 0\
**Last updated:** [October 2, 2026, 2:40pm UTC](https://devcommunity.amd.com/t/building-your-first-agent-with-gaia-stop-guessing-ask-your-gpu/1130 "2026-10-02T14:40:13Z")
You’ve done this before: find a model that looks perfect, pull it down, hit run — and watch your machine choke, or worse, silently swap to disk and crawl. Then you’re back on a forum trying to reverse-engineer whether it…
---
## [Enabling Physical AI Agents with Lemonade](https://devcommunity.amd.com/t/enabling-physical-ai-agents-with-lemonade/925)
**Author:** [@Uncy\_AMD](https://devcommunity.amd.com/u/Uncy_AMD)\
**Replies:** 0\
**Last updated:** [August 29, 2026, 6:46pm UTC](https://devcommunity.amd.com/t/enabling-physical-ai-agents-with-lemonade/925 "2026-08-29T18:46:18Z")
In this blog we will demonstrate how to run local agents enabled by VLMs (Vision-Language Models) hosted by the Lemonade framework in the domain of robot control. These models allowed us to run an interactive robotic …