GioStrives

Striving to use AI and tech to improve our world...while documenting my journey.

[GioStrives @GioStrives]

https://t.co/WWFaATM6Xx

[GioStrives @GioStrives]

@enjojoyy Yes, that's why we need university courses!

[GioStrives @GioStrives]

@matteopelleg Source? I mean, maybe in a lab setting; but with me sitting next to it and heat coming in or going out from windows and heaters I honestly think removing background noise would be very hard.

[GioStrives @GioStrives]

@itsalicesoul That's a joke, of course the easiest programming language is Brainf*ck.

(That's another non funny joke)

[GioStrives @GioStrives]

@net_termina These architectures are too different to compare without real benchmarks.

An example: I have 1080s and 2080s. Qwen image 2.1 on 2080s is about 30x faster. Why? 1080s have no Tensor Cores and so have no optimisation for FP16.

Not to mention all these cards can't use bf16...

[GioStrives @GioStrives]

@BlastBurn27 @ItsmeAjayKV VRAM is the bottleneck.

I managed to make it run on 1080s and 2080s so yeah, 3060 will be just fine.

[GioStrives @GioStrives]

@itsalicesoul It depends on your budget; they burn budgets so fast that I try to avoid using them, whenever possible.

[GioStrives @GioStrives]

Keep you posted. I mean, keep myself posted, I know I am the only one reading this...if time won't change that, at least I will have learned a lot 😊

This is the lesson btw: https://t.co/yV22VYINle

[GioStrives @GioStrives]

Stanford CS329A lecture 1 on YouTube surprised me.

I expect university courses to lag the field. This one cited the DeepSeek paper from December 2024 and walked through what AI research actually looks like now.

[GioStrives @GioStrives]

That’s the other gift of a course: too many papers get published and I often just collect them, without going in-depth.

A syllabus forces you to go deep on a few.

[GioStrives @GioStrives]

Do 1080s dream of electric sheep? I managed to run the new #qwen model on my 1080s.

They might be old cards, but they can handle this model. The only downside is that their architecture is very slow: I had to wait 15 minutes for this image...with the newer 2080s it took less than 3 to obtain the same result (consuming a lot less electricity)!

I'll post a more detailed analysis in the future, for now here's my result 😊 #Dreamer

[GioStrives @GioStrives]

@itsvishaltwt You're missing purely functional languages: where are Haskell and Lisp?

[GioStrives @GioStrives]

@danellisona No need to remark that: we know 😂

[GioStrives @GioStrives]

@themishra4402 Mine creates images! Just loaded the new qwen image model on my GPUs and wrapped it into a tool.

[GioStrives @GioStrives]

@loktar00 Which harness and api are you using? Do you know where the model is served?

I am doing something similar with qwen models locally but, so far, I am using this config only for simple tasks.

[GioStrives @GioStrives]

@giutheginger @KylieUncovered @Futana6 Sounds nasty; reminds me of how they hacked @LinusTech and many other YT channels: with fake sponsors...

[GioStrives @GioStrives]

@TheAidenWagner Talk about yourself, my whole car is way cheaper than 30k 😂