On release, there were a few people suggesting that there was nothing special about Gemma 4. This was missing the point - weight, Gemma 4 outperforms the current landscape of models and has tuning pipelines. This is the true value of Gemma 4.
There is a surplus of great models that are hostable locally, but not many members of the community have infinite VRAM. Most top out somewhere in 128G. What if we could pool our resources together and host models for each other?
Fedora works great on the newest Strix Halo machines. Combined with Lemonade Server, users can very easily get set up using models like Qwen3.5 using CPU, GPU, and NPU backends.
Lemonade Server and Goose on an AMD Strix Halo setup in good old Fedora linux rounds out the March '26 stack. AMD Strix Halo devices offer CPU, GPU, and NPU workloads that Lemonade Server can offer to Goose. A powerhouse (and power efficient) local AI host right on the desktop.
This is the first post in a line of what should be many. The goal is to have a good dumping ground of the things I like as we move forward. Why and How The landscape is pretty broad now that, in the lovely year of 2025, every well known