@0cc4m

6 Followers
12 Following
2 Posts
Open Source GPGPU Programming
Githubhttps://github.com/0cc4m/

I tested four Framework Desktop Mainboards with AMD Ryzen AI Max+ 395 (what a mouthful!) in a private AI cluster.

I've published *ALL* my test results (including testing the new gpt-oss-20b and 120b models, as well as giant LLMs across the full cluster), links are in the video description: https://www.youtube.com/watch?v=N5xhOqlvRh4

https://airlied.blogspot.com/2025/07/ramalamamesa-benchmarks-on-my-hardware.html I did some baseline benchmarks to help level set my brain towards fixing this.
ramalama/mesa : benchmarks on my hardware and open source vs proprietary

One of my pet peeves around running local LLMs and inferencing is the sheer mountain of shit^W^W^W complexity of compute stacks needed to ru...