Issues installing LM Studio with Fedora 42

Fedora 42

Which kernel are you using? -Latest

Which BIOS version are you using? -Latest

Which Framework Desktop model are you using? (AMD Ryzen™ AI Max 300 Series)

I’m having issues installing any LLM on the Framework Desktop. I initially tried using Ubuntu and had issues with iGPU, and no I am trying with Fedora 42. Ollama is giving an error related to no iGPU and LM Studio is giving an error related to libatk1.0-0.

Have you already seen this thread?

  • [Vulkan] Fixed a bug where models were not being loaded onto iGPUs (requires runtime update) (bug #1048).

May be solved with last release (did not test.)

Can confirm that the new Vulkan llama runtime update (1.52.1) fixes the issue