
Rodei um modelo MoE de 35B de parâmetros em uma RX 580 de 8GB de 2017 (e quase desisti três vezes)
Isso começou como uma pergunta idiota feita depois de já ter visto o Qwen3 4B rodando a 35 tokens/s...
Tag archive

Isso começou como uma pergunta idiota feita depois de já ter visto o Qwen3 4B rodando a 35 tokens/s...

Finally Vulkan computing possible on PS4 GPU vulkan compute array running on PS4 GPU(Gradius): Using...

Running Local AI on an AMD RX 580 in 2026 — The Complete Vulkan Guide "An RX 580 from 2017 running...
I wanted to live code in C++. Not a DSL that compiles to C++. Not a scripting language with bindings....

A $550 AMD GPU should be enough to do useful local AI. But if you actually try it, the stack...
A matrix is not a camera Vulkan does not have a camera. It has a push constant slot. If...
Understanding Integration Nuances: A VulkanMod Case Study In the intricate world of...

Hey folks 👋 So… this is my first ever post on graphics programming. I’m not a writer, but I figured...
1. Vulkan applications start by creating a Vulkan Instance that defines the Vulkan...
Here I am sharing a opensource software through which possibility to create lattice structure which...
The past months I embarked on a book writing project on accident; a book on low level graphics progra...
In my previous blog post yesterday, I shared my thoughts on graphics APIs and libraries. Another...