OsamaJaber

soon :)

you can give it a try

The comparison set is Gemma4-31B and Qwen3.6-27B, not the current Qwen Fair on size, but the headline numbers are against a model a generation back

Expanding free access is mostly an inference cost Serving cheaply at that scale means routing, batching, and cache hits, not a better model :D

The gap I've hit generating GPU kernels with agents code that compiles and runs fine but is slower than the baseline. Validator says pass, result is useless. Speed targets have to be part of the…

thread: https://x.com/Akashi203/status/2074495867449434389