Carlo(@Italianclownz):I'm loving the @FrameworkPuter Gorgon! 🔥 I've been running GLM 5.3 Flash and MiMo v2.6 Flash on the @AIatAMD Gorgon, and both have been stable, efficient, and FAST for models this large. I set GLM 5.3 Flash loose on a coding task overnight and woke up to completed code. That's what excites me about where local AI is headed. Long-running agentic workloads, powered entirely by local models on local hardware. Now I'm focused on squeezing even more performance out of both models. I also got the Lucebox engine running DeepSeek extremely well directly on the Gorgon! Next up is getting GLM 5.3 Flash and MiMo v2.6 Flash running properly in Lucebox and seeing how far we can push performance. @pupposandro @davideciffa @luceboxai Local AI keeps getting better. 🚀

2026.09.30 13:25

I'm loving the @FrameworkPuter Gorgon! 🔥 I've been running GLM 5.3 Flash and MiMo v2.6 Flash on the @AIatAMD Gorgon, and both have been stable, efficient, and FAST for models this large. I set GLM 5.3 Flash loose on a coding task overnight and woke up to completed code. That's what excites me about where local AI is headed. Long-running agentic workloads, powered entirely by local models on local hardware. Now I'm focused on squeezing even more performance out of both models. I also got the Lucebox engine running DeepSeek extremely well directly on the Gorgon! Next up is getting GLM 5.3 Flash and MiMo v2.6 Flash running properly in Lucebox and seeing how far we can push performance. @pupposandro @davideciffa @luceboxai Local AI keeps getting better. 🚀