Tag archive
Qwen3 llegó con thinking mode y mejoras reales en código. Pero antes de reemplazar el modelo que ya tenés corriendo en Ollama, hay preguntas técnicas que responder primero. Acá las respondo sin vender hype.
Qwen3 landed with thinking mode and real improvements in code generation. But before you replace the model already running in your Ollama setup, there are technical questions you need to answer first. I answer them here without selling hype.
The homelabber community is building local AI dev platforms and the discussion is genuinely interesting. I have some observations that go beyond the initial excitement — and a checklist so you can decide whether the experiment is actually worth it.
Gemma 4 runs offline on iPhone. I replicated it on my 13 with a nearly full 128GB. It works. But the gap between 'runs' and 'actually does something useful' is exactly the story of all mobile local inference — and what it does to the Apple-as-AI-laggard narrative is more interesting than the model i
Gemma 4 corre offline en iPhone. Lo repliqué en mi 13 con 128GB casi llenos. Funciona. Pero el gap entre 'corre' y 'sirve para algo concreto' es exactamente la historia de toda la inferencia local en mobile — y lo que esto le hace al argumento de Apple como rezagada de IA es más interesante que el modelo en sí.