Utrymme för lokal AI
Gratis att se, Pro för att ändra
Kontrollera om en lokal modell ryms i din Macs minne innan du hämtar eller läser in 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
Vad det gör
- Du väljer en modellfamilj och storlek, 4, 8 eller 16 bit, och en kontextlängd från 4K till 128K.
- Uppskattar vad den behöver (vikter, kontextcachen och körmiljö) och jämför med vad GPU:n kan använda och vad som är ledigt just nu.
- Svarar Ryms, Trångt, Skapa utrymme eller Ryms inte, med raden som avgjorde det.
- Skapa utrymme föreslår att starta om eller avsluta appar som håller minne, via Hedrooms vanliga åtgärder.
- Märker Ollama, LM Studio, Jan och GPT4All när de körs och säger vad de använder.
- Kan höja GPU-minnesgränsen tills du startar om, efter en bekräftelse som säger hur lite som blir kvar åt macOS.
What it will not do
- Hämta, läsa in eller köra en modell, eller prata med en modellapp.
- Lova hastighet. Det uppskattar bara minne.
- Erbjuda en gräns som lämnar macOS mindre än 8 GB.
- Höja gränsen utan din bekräftelse. När Hedroom avslutas sätter det tillbaka gränsen till vad den var, om du inte ändrat den själv.
Limits
- Uppskattningen kan avvika med cirka 15 %. Lager- och huvudtal är typiska för en modellfamilj, inte lästa från din fil.
- macOS publicerar inte sin standardgräns för GPU. Hedroom visar sin egen avläsning: ungefär två tredjedelar av minnet upp till 36 GB, tre fjärdedelar över det.
- På Mac-datorer med 8, 16, 18 eller 24 GB erbjuder Hedroom ingen högre gräns, eftersom det mesta det skulle tillåta inte är mer än macOS redan ger GPU:n.
- Att höja gränsen kräver samma hjälpprogram som fläktstyrning, som kräver godkännande i Systeminställningar. En högre gräns lämnar mindre åt macOS, och din Mac kan bli långsam eller instabil om minnet tar slut. Den gäller tills du startar om.
Gratis eller Pro
Kontrollen och avläsningen av GPU-minnesgränsen är gratis. Att höja gränsen ingår i Pro. Att återställa den är 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.