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…
TOOLS
-
Criticism of Ollama and recommended alternatives for LLM deployment
By
–
-
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
-
SambaCloud: Seamless OpenAI Alternative for Developers
By
–
Want to see how easy it is to choose SambaCloud?
— SambaNova (@SambaNovaAI) 25 mars 2026
Just set your OPENAI_API_KEY to SambaNova’s, update the base URL, pick your model, and go. Seamless transition from OpenAI and others. 🙌https://t.co/RrTVxRQWb2 pic.twitter.com/Jk5TEfVuUJWant to see how easy it is to choose SambaCloud? Just set your OPENAI_API_KEY to SambaNova’s, update the base URL, pick your model, and go. Seamless transition from OpenAI and others. https://
sambanova.ai/products/samba
cloud?utm_source=x&utm_medium=organic&utm_campaign=developer
… -

OpenAI Debuts Major ChatGPT Ads Updates, Including Self-Serve Manager and CPC Bidding
By
–
Most interesting image from this article Everyone changed from classic incadescent lamps to modern LEDs But they don't provide any infrared light Even the warm LEDs you buy barely do We really need incadescent lights back but the EU made those illegal, or we need to buy those
-

Building a Computer Inside a Transformer: Code and Weights Released
By
–
1/4 Want to build a computer inside a transformer? Given the wide interest in our project, we are releasing the code and the weights so that others can build on our construction. [Translated from EN to English]
→ View original post on X — @thegautamkamath, 2026-03-25 20:50 UTC
-
Warning: Do Not Use Windows for Local LLM Deployments
By
–
I was assuming it’s common knowledge at this point not to use Windows for local LLMs But just in case: DO NOT USE Windows for local LLMs
-
Scaling Brand Consistency with AI Video Automation
By
–
La mayoría de equipos no tiene un problema de creatividad. Tiene un problema de consistencia. Cada vídeo es rehacer lo mismo: colores, fuentes, logos… una y otra vez. Si el branding deja de ser un ajuste manual y pasa a estar integrado en el sistema, escalar contenido deja de x.com/HeyGen/status/…
-
Spec Sheet Irrelevance Due to Missing Software
By
–
go buy both and you’ll see how all you’re repeating from the spec sheet doesn’t matter because the software doesn’t exist for it lol
-
Norm: AI Phone Agents Built Instantly from Prompts
By
–
Never a dull moment in AI!
— Charly Wargnier (@DataChaz) 25 mars 2026
The era of "prompt-to-phone-agent" is here.
Meet Norm.
Literally just tell Norm the phone agent you want → Norm builds it for you → Automate your calls instantly 👀 https://t.co/BDJmPreRxeNever a dull moment in AI! The era of "prompt-to-phone-agent" is here. Meet Norm. Literally just tell Norm the phone agent you want → Norm builds it for you → Automate your calls instantly
-
Developer shares experience with Supabase backend platform
By
–
Also love Supabase but haven’t had a need for it recently.