Plads til lokal AI
Gratis at se, Pro for at ændre
Tjek, om en lokal model kan være i din Macs hukommelse, før du henter eller indlæser den.
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
Hvad den gør
- Du vælger en modelfamilie og størrelse, 4, 8 eller 16 bit, og en kontekstlængde fra 4K til 128K.
- Estimerer, hvad den skal bruge (vægte, kontekstcache og runtime), og sammenligner så med, hvad GPU'en kan bruge, og hvad der er ledigt lige nu.
- Svarer Passer, Knap, Gør plads eller Passer ikke, med den linje, der afgjorde det.
- Gør plads foreslår at genstarte eller afslutte apps, der holder på hukommelse, gennem Hedrooms almindelige handlinger.
- Opdager Ollama, LM Studio, Jan og GPT4All, når de kører, og siger, hvad de bruger.
- Kan hæve GPU-hukommelsesgrænsen, indtil du genstarter, efter en bekræftelse, der siger, hvor lidt der er tilbage til macOS.
What it will not do
- Hente, indlæse eller køre en model eller tale med en modelapp.
- Love hastighed. Den estimerer kun hukommelse.
- Tilbyde en grænse, der efterlader macOS mindre end 8 GB.
- Hæve grænsen uden din bekræftelse. Når Hedroom lukker, sætter den grænsen tilbage til det, den var, medmindre du selv har ændret den.
Limits
- Estimatet kan afvige med cirka 15 %. Tal for lag og hoveder er typiske for en modelfamilie, ikke aflæst fra din fil.
- macOS offentliggør ikke sin standard-GPU-grænse. Hedroom viser sin egen aflæsning: cirka to tredjedele af hukommelsen op til 36 GB, tre fjerdedele derover.
- På Mac-computere med 8, 16, 18 eller 24 GB tilbyder Hedroom ikke en højere grænse, fordi det mest, den ville tillade, ikke er mere, end macOS allerede giver GPU'en.
- At hæve grænsen kræver den samme hjælper som blæserstyring, som skal godkendes i Systemindstillinger. En højere grænse efterlader mindre til macOS, og din Mac kan blive langsom eller ustabil, hvis hukommelsen slipper op. Den gælder, indtil du genstarter.
Gratis eller Pro
Tjekket og aflæsningen af GPU-hukommelsesgrænsen er gratis. At hæve grænsen er en del af Pro. At nulstille den er aldrig låst.
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.