KickMint is built the other way. The AI runs on your phone.
What this means in practice
When you open the app for the first time, KickMint offers a one-time download. About 900 megabytes over WiFi, the size of a short film. The file is Qwen 2.5 1.5B Instruct, an open-weight model from Alibaba Cloud, quantized to Q4_K_M to fit on a phone (roughly one gigabyte). It downloads from our R2 bucket at models.kick-mint.com. The SHA-256 hash of the file is published in the manifest and verified after download.
After that, every AI feature, the task breakdowns, the Pick One suggestions, the Stuck recoveries, the Weekly Review summaries, runs against that file using llama.cpp. The inference happens on the Neural Engine and the CPU of your iPhone. No prompt and no completion ever leaves the device.
To verify this for yourself: turn on airplane mode after the model is downloaded. Every AI feature continues to work.
What about sync
Sync is optional and only available on KickMint Pro. When you pair two devices, KickMint generates an AES-256-GCM symmetric key on your phone, paired with an Ed25519 signing key. Your task data is encrypted on device, signed on device, then uploaded to sync.kick-mint.com as opaque ciphertext blobs. The server stores the blobs for at most 90 days, then deletes them automatically.
The server has no key material. We could not read your data even if we wanted to. The blobs are useless to anyone who does not have the device-resident key.
If you never enable sync, our infrastructure never sees a request from your phone after the model download.
Why we chose this architecture
Three reasons.
First, the people we serve disclose more in private writing than in shared tools. ADHD and AuDHD adults often write down what they are actually avoiding, what is actually overwhelming them, what they are actually ashamed of. Those notes are the raw material the breakdown model uses to be useful. The breakdowns are only useful when the user is honest, and the user is only honest when the system gives them no reason to perform.
Second, server-side AI is a forever-cost. We would have to pass it on to you. The cloud bill scales with daily active users, and the only way to keep the price down at scale is to upsell tiers, mine usage, or insert ads. We did not want any of those incentive structures.
Third, regulatory durability. The on-device model is unaffected by any future jurisdiction-specific privacy regulation, because there is no data flow to regulate. The decision once, hold forever.
The model itself
- Architecture: Qwen 2.5 1.5B Instruct, a transformer with 1.5 billion parameters.
- Quantization: Q4_K_M, four-bit weights with selected weights at higher precision.
- File size on device: approximately 986 MB.
- Runtime: llama.cpp 0.x via SwiftCpp bridging, Metal-accelerated where available.
- License: Apache 2.0 (Qwen 2.5 weights are released under Apache 2.0 by Alibaba Cloud).
- What we did not modify: the weights. We use the published Qwen 2.5 1.5B Instruct release exactly as Alibaba shipped it. We re-host the GGUF on our CDN for download stability.
- What we did add: our own prompt scaffolding, the verb allowlist that enforces physical-first first actions, the rationale catalog, and the parser that rejects malformed JSON or banned phrases. Those are the layers that turn a general-purpose model into the ADHD-focused task helper.
When the model is unavailable
If the user skips the download or deletes the model file, KickMint falls back to rule-based templates for breakdowns and Pick One. The free templates are good enough to use the app for the daily loop. The on-device AI is the upgrade, not the floor.
If you want to verify this technically
- Source layout:
iosApp/Sources/AI/ModelManager.swift(download lifecycle),iosApp/Sources/AI/LlamaInference.swift(inference),iosApp/Sources/AI/BreakdownParser.swift(output validation). - The egress audit lives in
iosApp/Tests/Security/RemoteFeatureFlagsEgressTests.swiftandiosApp/Tests/Sync/SyncEgressTests.swift. A clean install with no Pro entitlement emits zero requests to sync.kick-mint.com. - The privacy policy lives at /privacy. The full citation library is at /science.
KickMint is a productivity tool, not a medical device. Medical disclaimer at /medical-disclaimer.