iOS app

Know which AI models your phone can actually run.

WillItRun reads your device's real allocatable memory ceiling, not total RAM, and tells you instantly which on-device AI models (GGUF format) will run great, run marginally, or not fit at all. No downloads. No experiments. Just a clear verdict.

Download on the App Store View privacy policy

On-device only. No personal data collected.

WillItRun home screen showing the device memory budget and a See Which Models Run button

Real memory ceiling

Not total RAM. Your real budget.

iOS reserves a large chunk of RAM for itself. WillItRun probes what your app actually gets, the number that decides whether a model loads or crashes.

Instant fit check

Every model. Clear verdict.

RUNS GREAT, MARGINAL, or WILL NOT FIT, for every GGUF model in the catalog, ranked and colour coded. No test runs. No wasted downloads.

Model fit results listing Gemma 3 1B as RUNS GREAT and several models as MARGINAL

Context matters

Drag the slider. Watch verdicts flip.

Context window size changes KV cache needs dramatically. Slide from 4K to 128K tokens and watch which models stay green, turn amber, or drop out.

Context length slider set to 16K tokens, showing updated model verdicts

Memory breakdown

Full breakdown, no guessing.

Resident weights, KV cache, scratch buffers, runtime base, evictable weights, total footprint, survivable ceiling. Plus TTFT and burst speed from your real bandwidth.

Gemma 3 1B detail screen with a memory breakdown: KV cache, weights, TTFT, burst speed

GGUF URL analyzer

Analyze any model before you pull it.

Paste a Hugging Face URL. WillItRun reads 64 KB of metadata over an HTTP range request. No weights downloaded. No storage used.

Analyze GGUF URL screen with a paste field and an Analyze button

WillItRun collects no personal data. On-device only.

Read the full privacy policy