@FaztTech A mí no me gusta programar pero si me encanta saber cómo funciona jajajaja jajajaja así que esto directamente me potencio y sobre todo que este año me pase a CACHYOS el cambio fue GIGANTESCO!!!
@HilarioTZ1@FaztTech jajajajaj SIEMPRE APARECE ESTOS PAYASOS QUE CREEN TENER LA RESPUESTA MORAL A TODO JAJAJAJ cerra el ANO, cara termo que nadie quiere saber lo moralmente alto que te sentis diciendo cosas obvias a nadie le interesa
@Radio10@pabloduggan@rosarioa NINGUNO SE PUSO A LEER NADA!!!!!! YO NO PUEDO CREER LA IGNORANCIA DE ESTOS ZURDOS DE MIERDA!! jajajaja asi quieren volver?? si se pusieran a leer el proyecto SE VAN A DAR CUENTA QUE ERA NECESARIO esa "Ley de Manejo del Fuego"
@RespOficial_Arg@JMilei SE LES TERMINA LA JODA ZURDA A TODA LA REGION!!! perdieron TODA CREDIBILIDAD!!! MILEI ESTA GRITANDO HACE AÑOS QUE TODA ESTA MAFIA TRABAJA JUNTA HACE DECADAS y hoy ya no disimulan! es obvio que el movimiento ANTIARGENTINA ESTA ORQUESTADO POR LOS COMUNISTAS/SOCIALISTAS DE M13RDA
@nataliavolosin@tipitoenojado UN ZURDO HIPOCRITA CONTRADICIENDOSE es lo mas normal del mundo NOSE QUE LES EXTRAÑA QUE LLOREN POBREZA Y SE ALIMENTAN DE LOS IMPUESTOS DEL POBRE JAJAJA HIPOCRITAS
@porqetendencias ZURDOS DE M13RDA!!!!!! odian a Messi y a la selección y se nota que tiran la piedra y esconden la mano y cuando lo descubren se victimizan
Let me show you why we are living in a singularity right now.
I just turned an 8GB VRAM budget laptop into a fully autonomous, self improving local AI Agent.
In the previous post, I showed you how Google's QAT quants allow you to run the massive Gemma 4 26B MoE model locally on a 8GB VRAM + 16 GB RAM laptop.
The community was stunned. But now, we are going far beyond chat.
Nous Research just shipped their official Hermes Agent Desktop App this week.
I hooked my local llama server up to the Hermes Desktop App. The integration took exactly 2 minutes. What I witnessed next was absolutely mind bending.
you can run a state of the art, 24/7 autonomous agentic ecosystem with full tool execution, locally, on a laptop with:
- Intel i5 or i7 | 16GB System RAM
- Any 8GB VRAM GPU (like my RTX 4060)
My local 26B model is now behaving like a developer, system admin, and personal assistant rolled into one.
Here is what this local 8GB setup can do for me out of the box:
Autonomous Software Engineering: It doesn't just write code; it reads, edits, and patches files, runs them in a secure terminal, systematically debugs errors, manages GitHub repos, and spawns sub agents to tackle complex pipelines in parallel.
Web Interaction & Vision: It browses the web like a human, clicks buttons, visualizes layouts via Vision to debug UI, and scrapes arXiv papers.
DevOps & Automation: It schedules natural language cron jobs, manages containerized background processes, and runs Python RPC scripts.
Workspace Orchestration: It connects directly to Notion, Google Workspace, Linear, and Obsidian to manage tasks.
The Local Hardware Performance
Running a 26B parameter model and an autonomous agent framework simultaneously on an 8GB VRAM card should be impossible. Here is how it performs:
- Stable, flat speed even with massive context. I threw a 60k token prompt at it, and it still clocked 20 TPS.
Llama.cpp flags:
llama-server.exe -m "gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf" -cmoe -c 248000 -v
Kudos to @Teknium and the entire @NousResearch team.
The barrier to entry for the agentic age has officially collapsed. What are you building first?