Margem para IA local
Grátis para ver, Pro para mudar
Veja se um modelo local cabe na memória do seu Mac antes de baixá-lo ou carregá-lo.
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
O que faz
- Você escolhe uma família e um tamanho de modelo, 4, 8 ou 16 bits, e um tamanho de contexto de 4K a 128K.
- Estima o que ele precisa (pesos, cache de contexto e runtime) e compara com o que a GPU pode usar e o que está livre agora.
- Responde Cabe, Apertado, Abra espaço ou Não cabe, com a linha que decidiu.
- Abra espaço sugere reabrir ou encerrar apps que seguram memória, pelas ações normais do Hedroom.
- Percebe Ollama, LM Studio, Jan e GPT4All quando estão em execução e diz o que eles usam.
- Pode aumentar o limite de memória da GPU até você reiniciar, depois de uma confirmação que diz quanto sobra para o macOS.
What it will not do
- Baixar, carregar ou executar um modelo, ou falar com um app de modelo.
- Prometer velocidade. Ele só estima memória.
- Oferecer um limite que deixe menos de 8 GB para o macOS.
- Aumentar o limite sem a sua confirmação. Quando o Hedroom é encerrado, ele devolve o limite ao que era, a menos que você o tenha alterado.
Limits
- A estimativa pode errar em cerca de 15%. Os números de camadas e cabeças são típicos de uma família de modelos, não lidos do seu arquivo.
- O macOS não publica o limite padrão de GPU. O Hedroom mostra a sua própria leitura: cerca de dois terços da memória até 36 GB, três quartos acima disso.
- Em Macs com 8, 16, 18 ou 24 GB, o Hedroom não oferece um limite maior, porque o máximo permitido não passaria do que o macOS já dá à GPU.
- Aumentar o limite precisa do mesmo auxiliar do controle dos ventiladores, que exige aprovação em Ajustes do Sistema. Um limite maior deixa menos para o macOS, e seu Mac pode ficar lento ou instável se a memória acabar. Dura até você reiniciar.
Grátis ou Pro
A verificação e a leitura do limite de memória da GPU são grátis. Aumentar o limite faz parte do Pro. Redefinir nunca é 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.