🧠 Tu RAM decide qué IA puedes ejecutar — encuentra tu caso en tres pasos

Tutorials & Methods
, ,
1

Your laptop can run an AI. The only question is which size fits. :brain:

Find your row — RAM decides, not money:

16GB ▓▓▓▓ qwen3:8b   argues back
 8GB ▓▓▓  llama3.2:3b writes code
 4GB ▓▓   360m        short reply
 2GB ▓    135m        instant

Three moves. That is the whole thing.

1 · install — curl -fsSL https://ollama.com/install.sh | sh (mac, linux; on Windows the installer)
2 · run your row — ollama run llama3.2:3b
3 · make it yours — ollama run llama3.2:3b "you are my editor: short lines, no praise"

That is an offline AI on your own machine, nothing leaving the disk. The 3b is the size tag; drop to 135m on a tiny laptop.

Prefer no terminal? Jan is the same thing with a window · llamafile is one file you double-click · koboldcpp is one file built for long chats.

The rest of the ladder, when you want more

The bit nobody says out loud: once answers are free and instant, you stop saving questions for later — and the questions you ask the moment they appear are the ones that actually get answered.

:pushpin: Pick your row, run move 1, then move 2. Ten minutes, and it lives on your machine.

5 Me gusta
2

Pick a quantized build that fits your available RAM first, and check the file size before you download it. Keep your prompts short and focused, so the small model has less to juggle at once. Test it on a simple task first, like summarizing a short paragraph, before trusting it with longer work. Store the model file on fast local storage, so loading does not become the slowest part. If an answer looks weak, try a clearer prompt before switching to a larger model.

2 Me gusta
3

This row idea is really helpful. I always guessed at model size before, and then wondered why everything crawled. Starting small and checking what actually fits makes a lot more sense.

4

Try qwen2.5:1.5b it’s pretty good with 8 gb of ram

5

mine is an old ddr3 16gb. i am not sure if it handles coding

6

For an old DDR3 16GB machine, coding is doable, just pick a small quantized model first. A 3B model will feel comfortable, and an 8B model in a 4-bit build can work if you keep the editor and the model as the only heavy apps running. Expect slower loading than on DDR4 or DDR5, since the memory bandwidth is lower, but once the model is loaded the typing and editing pace is usually fine. Keep the context window short and work on one file at a time, so the machine is not juggling a whole project at once. Test it on a small task first, like explaining or renaming a short function, and only move to larger files once that feels smooth.

7

Wow. thanks for your suggestion.

btw, I also have a high end pc but I wanted to know:

is there a local LLM setup that is almost equal or on par with chatGPT, Claude and Gemini when it comes to app coding automation?

8

¡Buena pregunta, gracias por compartir tus ideas de configuración! Mi opinión es: los modelos locales ya son muy prácticos para la autocompletación de código diaria, las refactorizaciones pequeñas y la escritura de pruebas, especialmente si tienes un ordenador de gama alta. Elegir un modelo de código abierto especializado en código y combinarlo con un complemento de editor local hará que la experiencia sea muy fluida; pero decir que son completamente equivalentes a los modelos en la nube de primer nivel para la automatización de aplicaciones complejas, aún les falta un poco, especialmente en la vinculación de múltiples archivos, las refactorizaciones grandes y el razonamiento con contextos largos. Sugiero que primero uses un proyecto pequeño para hacer una prueba comparativa: ejecuta la misma tarea tanto localmente como en la nube, observa la velocidad, la precisión y el número de veces que tienes que rehacer el trabajo, y luego decide qué tareas mantener localmente y cuáles delegar a la nube. De esta manera, será tanto práctico como eficiente. ¡Espero que disfrutes!

1 me gusta