Carlo
@Italianclownz
4GQTV Producer | Bylines: WIRED | AI + Open Source Dev | Building ROCmFPX đ | | | â
4.3K Following 7.3K Followers
I'm loving the @FrameworkPuter Gorgon! đĨ
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. đ
Show more
@MiaAI_lab @harderthanfire @jauneclaude I am installing Linux on the 9700 AI Pro dev machine and I will definitely take a look and see what can be done.
Seeing ROCmFPX make it into Arch Linux has me in the feels. Love Arch. Whoever did that, thank you.
I have been working hard on ROCmFPX the last two days and now you can run NVFP4 natively inside ROCmFPX on AMD Hardware. You no longer need to convert it, just download and go. MTP works too.
This is a pretty big update because in the past you needed to do a conversion and you can still do conversions (only if you want to) from NVFP4 - ROCmFP4. That's also been made better.
Next updates I am working on are better ROCmFP2 and ROCmFP3.
My goal is simple. Make ROCmFPX work on any and all AMD hardware whether you run Windows or Linux. It's optimized for ALL AMD Hardware. Well, RDNA 1 through RDNA 4 etc. And yes, this in theory should run on your Asus Rog Ally's too. Z1 and Z2.
Show more
