yeah that makes sense, thx. impressive and cool to see this working! will poke around a bit more 🙂
COMPUTING
-
Hyper-realistic AI-powered robots transforming future interaction
By
–
Hyper-realistic #Robots powered by #AI are reshaping the future of interaction
— Ronald van Loon (@Ronald_vanLoon) 26 mars 2026
by @Khulood_Almani
#Robotics #Engineering #ArtificialIntelligence #Innovation #Technology pic.twitter.com/6uETYfqXQPHyper-realistic #Robots powered by #AI are reshaping the future of interaction
by @Khulood_Almani #Robotics #Engineering #ArtificialIntelligence #Innovation #Technology -
Regret not maxing out RAM in summer PC build
By
–
I’m low key sad I didn’t max out my ram in my last build this past summer
-
The Rise of Hyper-Realistic Robots Powered by AI
By
–
The Rise of Hyper-Realistic #Robots Powered by #AI
— Ronald van Loon (@Ronald_vanLoon) 25 mars 2026
by @Khulood_Almani#Robotics #Engineering #ArtificialIntelligence #Innovation #Technology pic.twitter.com/JZjFKkn824The Rise of Hyper-Realistic #Robots Powered by #AI
by @Khulood_Almani #Robotics #Engineering #ArtificialIntelligence #Innovation #Technology -
Hardware options for Apple and non-Apple devices
By
–
For Apple hardware you’ve got no other option. For non-Apple hardware you’d be wasting your time.
-
Linux, LMStudio, and Exl2/Exl3 for AI Enthusiasts
By
–
Move to Linux and try LMStudio and then Exl2/Exl3
-
Criticism of Ollama and recommended alternatives for LLM deployment
By
–
just a gentle reminder that nobody should use ollama > slower than llama.cpp on windows
> slower than mlx on mac
> slop useless wrapper
> literal code thieves alternatives? > lmstudio
> llama.cpp
> exllamav2/v3
> vllm
> sglang
> trt-llm literally anythingʼs better than ollama x.com/stevibe/status… -
DGX Sparks Utilize Custom Linux for Enhanced AI Computing
By
–
Yeah. There’s a reason DGX Sparks are delivered with a pre-installed custom Linux image for example…
-
24B Model Running in Browser with WebGPU Technology
By
–
24B model running in your browser! https://t.co/dorx4Ux2x7
— Maxime Labonne (@maximelabonne) 25 mars 202624B model running in your browser! Xenova (@xenovacom) WebGPU is INSANE! 🤯 Here's a 24B parameter model running locally in a web browser, at a blazing ~50 tokens/second on my M4 Max. ⚡️ It's the largest model we've ever run with Transformers.js… and we're not stopping here. Big announcement soon. — https://nitter.net/xenovacom/status/2036908326462665211#m
→ View original post on X — @maximelabonne, 2026-03-25 21:10 UTC
-
Abstractions hinder performance, bare metal is optimal
By
–
Abstractions are not great for performance Bare metal is the way to go imho