Alex Ziskind
13.4K posts

Alex Ziskind
@digitalix
Developer and content creator, founder of @NativeScripting, ”the voice of NativeScript”, trainer, author, speaker, synth tweaker. https://t.co/ZjhwZDX24l




Comparison of Gemma 4 and Qwen 3.6 in the same coding task Same hardware, same prompt, comparable model size > gemma 4 31b: 27 tok/s, 3m 51s, 6,209 tokens, stronger game logic > qwen 3.6 27b: 32 tok/s, 18m 04s, 33,946 tokens, better visuals Gemma 4 with lower tok/s finished 14 minutes faster because it used 5.5x fewer tokens to reach a complete answer

Faces of the future. @Ominousind @wbznewsradio









4 hours of grinding. Running on untested branches to make nvidiva gb10 chip work with mac studio on the same cluster. But I got it working now @exolabs! Running Qwen 3.5 27b, 2100+ t/s prefill speed on my gx10, 19 t/s on studio, 4200ms ttft. Not bad before optimization.



video here: youtu.be/D2oZHzC_M28







