Margen para IA local
Ver es gratis, cambiar es Pro
Verifica si un modelo local cabrá en la memoria de tu Mac antes de descargarlo o cargarlo.
The problem
Downloading a local model is a long wait, and the failure comes at the end: it will not load, or it loads and your Mac starts swapping. The size on the download page is only part of the answer, because the context length you choose adds memory too.
Local AI headroom answers the question first. You pick the model size and context. Hedroom estimates what it needs, compares that with what your Mac can give a model right now, and names the line that decided the answer.
How it works
- Pick. Choose a model family and size, 4-, 8- or 16-bit, and a context from 4K to 128K. Hedroom names families and sizes only; it recommends no product.
- Estimate. It adds up the weights, the context cache (which grows with the context) and runtime overhead, each shown as "about". A 15% margin covers the fact that layer and head counts are typical for a family, not read from your file.
- Compare. The total is checked against the GPU memory limit and against what is free right now (free memory plus cached files; compressed memory does not count).
- Answer. Fits, Tight, Make room or Won't fit, with the line that decided it.
- Act, if you choose. Make room lists apps to relaunch or quit through the normal safety checks. On some Macs, Hedroom can raise the GPU limit until you restart, after a confirmation.
What you will see
A big verdict, "Fits.", "Tight.", "Fits, after making room." or "Won't fit.", with a sentence naming the line that decided it and the parts of the estimate: "Weights about … · context about … · runtime about … The estimate can be off by about 15%." A gauge shows what the model needs against two markers: what the GPU can use and what is free right now.
Beside it sits the GPU memory limit control, with a warning always on screen (less memory for macOS, your Mac can slow down or become unstable, it lasts until you restart), and a list of model apps Hedroom finds running: Ollama, LM Studio, Jan and GPT4All, with what they use. On a 16 GB Mac the limit control is off and says why.
A worked example
Example, not real data
A mid-size model on a 16 GB Mac
Say you want to try a Llama-family model at 8B parameters, 4-bit, with an 8K context. Hedroom estimates weights of about 4.8 GB, context of about 1.1 GB and runtime of about 0.8 GB: about 6.7 GB, or about 7.7 GB with the margin.
macOS lets the GPU use about two-thirds of a 16 GB Mac's memory by default, around 10.7 GB, so the GPU limit is not the problem. But say Chrome and Slack are open and free memory plus cached files reads about 7 GB. The low estimate fits and the high one does not, so the verdict is Tight, and the Make room list shows which apps hold the most. Hedroom promises no speed: it estimates memory only.
Details and limits
Qué hace
- Eliges una familia y un tamaño de modelo, 4, 8 o 16 bits, y una longitud de contexto de 4K a 128K.
- Estima lo que necesita (pesos, la caché de contexto y el tiempo de ejecución) y lo compara con lo que la GPU puede usar y con lo que está libre ahora mismo.
- Responde Cabe, Justo, Hacer espacio o No cabe, con la línea que lo decidió.
- Hacer espacio sugiere reabrir o cerrar apps que retienen memoria, mediante las acciones normales de Hedroom.
- Detecta Ollama, LM Studio, Jan y GPT4All cuando están en ejecución y dice qué usan.
- Puede subir el límite de memoria de la GPU hasta que reinicies, tras una confirmación que dice cuánto queda para macOS.
What it will not do
- Descargar, cargar o ejecutar un modelo, ni comunicarse con una app de modelos.
- Prometer velocidad. Solo estima la memoria.
- Ofrecer un límite que deje a macOS menos de 8 GB.
- Subir el límite sin tu confirmación. Cuando Hedroom se cierra, devuelve el límite a como estaba, salvo que lo hayas cambiado tú mismo.
Limits
- La estimación puede variar en torno a un 15 %. Los números de capas y cabezas son típicos de una familia de modelos, no se leen de tu archivo.
- macOS no publica su límite de GPU predeterminado. Hedroom muestra su propia lectura: unas dos terceras partes de la memoria hasta 36 GB y tres cuartas partes por encima.
- En Mac con 8, 16, 18 o 24 GB, Hedroom no ofrece un límite más alto, porque lo máximo que permitiría no es más de lo que macOS ya da a la GPU.
- Subir el límite necesita el mismo ayudante que el control de ventiladores, que requiere aprobación en Configuración del Sistema. Un límite más alto deja menos memoria a macOS, y tu Mac puede ir más lento o volverse inestable si la memoria escasea. Dura hasta que reinicies.
Gratis o Pro
La verificación y la lectura del límite de memoria de la GPU son gratuitas. Subir el límite forma parte de Pro. Restablecerlo nunca está bloqueado.
Raising the limit changes how your Mac behaves, which is why it is Pro.
Questions people ask
Does Hedroom download or run the model?
No. It never downloads, loads or runs a model, and never talks to a model app. It estimates memory and notices which model apps are running.
How accurate is the estimate?
It can be off by about 15%. The weights come from a simple formula, and layer and head counts are typical for the family, not read from your file. The verdict checks both the estimate and the estimate plus margin, so a borderline case reads Tight rather than Fits.
Is raising the GPU memory limit safe?
It leaves less memory for macOS, and your Mac can slow down or become unstable if memory runs short. Hedroom never offers a limit that leaves macOS less than 8 GB, shows how little is left before you confirm, puts the limit back when it quits, and the setting goes away at restart anyway.
Does it need the helper?
Checking is free and needs no helper. Raising or resetting the limit uses the same helper as fan control, which requires approval in System Settings. Approving the helper has the steps.