Can an iPhone app answer “Does he like me?” using an on-device model? The maker of 他爱我吗 describes an experiment that compares a user’s candidate answers against a supplied question and context, then displays relative scores. Those scores indicate preference among the options—not the other person’s feelings or the probability that he is in love.
In a DEV Community article, yang9527 identifies themself as the maker of 他爱我吗 and says the article was prepared with AI assistance from implementation notes. The app architecture and behavior below are therefore the maker’s account, not an independent review or validation.
| # | Preview | Product | Price | |
|---|---|---|---|---|
| 1 |
|
Apple iPhone 14, 128GB, Midnight - Unlocked (Renewed) | $300.00 | Buy on Amazon |
| 2 |
|
Apple iPhone 16, 128GB, Pink - Unlocked (Renewed) | $552.01 | Buy on Amazon |
| 3 |
|
Apple iPhone 15, 128GB, Black - Unlocked (Renewed) | $409.99 | Buy on Amazon |
| 4 |
|
Apple iPhone 13, 128GB, Midnight - Unlocked (Renewed) | $262.00 | Buy on Amazon |
| 5 |
|
Apple iPhone 16e, 128GB, Black - Unlocked (Renewed) | $388.34 | Buy on Amazon |
As an Amazon Associate I earn from qualifying purchases.
How the app’s local decision flow works
The experiment uses a Core ML conversion of laya-multilingual. Rather than generating an open-ended conversation, it asks the model to compare candidate answers supplied by the user. For a relationship question, those choices might express affection, no affection, or uncertainty.
- Enter a question and context. The user describes the situation and provides possible answers for the model to compare.
- Transcribe speech if needed. The maker says Chinese speech is transcribed locally with SenseVoice.
- Run the comparison. The app passes the question, context, and candidate answers to Laya through Core ML.
- Show relative scores and a templated response. The model compares the options; short conclusions and suggestions are assembled with templates.
The maker says history remains on the device and that the app does not call the Jev API or run the related Jev-compatible server. That describes the reported implementation; it is not an independent audit of every data flow.
#1 Best Overall
- This phone is unlocked and compatible with any carrier of choice on GSM and CDMA networks (e.g. AT&T, T-Mobile, Sprint, Verizon, US Cellular, Cricket, Metro, Tracfone, Mint Mobile, etc.).
- Please check with your carrier to verify compatibility.
- The device does not come with headphones or a SIM card. It does include a generic (Mfi certified) charging cable.
- Tested for battery health and guaranteed to have a minimum battery capacity of 80%.
What a displayed score can—and cannot—tell you
yang9527 describes the result this way: “A displayed answer score is a relative preference among the options given to the model.” A higher score means the model favored one supplied option in that comparison. It is not a measured probability that someone loves you, nor evidence of that person’s private thoughts.
Adding context can help frame the comparison, but it cannot give a model access to another person’s internal state. As the maker puts it, “A model cannot see the other person’s thoughts, and an attractive percentage does not change that.” Any result should therefore be read as a model output shaped by the wording and options provided—not as psychological certainty.
Rank #2
- 6.1" Super Retina XDR OLED, HDR10, Dolby Vision, 1000nits (typ), 2000nits (HBM), 2556x1179px at 460ppi, 3561mAh Battery
- 128GB 8GB RAM, Apple A18 (3nm), Hexa-core (2x4.04 GHz + 4x2.20 GHz), Apple GPU 5-core, 16‑core Neural Engine
- Rear camera: 48MP, f/1.6, wide + 12MP, f/2.2, ultrawide, Front Camera: 12MP, f/1.9, wide, iOS 18, upgradable to iOS 18.5
- 4G LTE: 1/2/3/4/5/7/8/12/13/14/17/18/19/20/25/26/28/29/30/32/34/38/39/40/41/42/48/53/66/71, 5G: n1/2/3/5/7/8/12/14/20/25/26/28/29/30/38/40/41/48/53/66/70/71/75/76/77/78/79 - Dual eSIM
- Unlocked for freedom to choose your carrier. Compatible with both GSM & CDMA networks. The phone is unlocked to work with all GSM Carriers & CDMA Carriers Including AT&T, T-Mobile, Verizon, Sprint., Etc.
Model size, storage, and input limits
The system-one-foundation-models mobile deployment guide describes laya-multilingual as a 322-million-parameter model and estimates these sizes for its Core ML conversions:
| Conversion described in the guide | Estimated model size |
|---|---|
| FP32 | About 1.28 GB |
| FP16 | About 644 MB |
| 8-bit quantized Core ML | About 160 MB |
These are documentation estimates, not measurements of the app’s download size or runtime behavior. The guide reports a Brier-score impact below 0.005 for its quantization conversion; that figure belongs to the conversion described there and does not establish relationship-judgment accuracy.
Rank #3
- 6.1inch Super Retina XDR display. Aluminum with color-infused glass back. Ring/Silent switch
- Dynamic Island. A magical way to interact with iPhone. A16 Bionic chip with 5-core GPU
- Advanced dual-camera system. 48MP Main | Ultra Wide. Super-high-resolution photos (24MP and 48MP). Next-generation portraits with Focus and Depth Control. 4X optical zoom range
- Emergency SOS via satellite. Crash Detection. Roadside Assistance via satellite
- Up to 26 hours video playback. USB C, Supports USB 2. Face ID
The same guide recommends on-demand resource delivery to manage app download size. It also warns that keeping a roughly 160 MB model resident may contribute to memory pressure on older devices with 4 GB of RAM. These are implementation considerations, not a confirmed compatibility list for 他爱我吗.
Input capacity depends on the deployment bundle. A laya.tools deployment guide updated September 25, 2026, describes one Neural Engine Core ML bundle with a 96-token total input limit and an alternate multilingual bundle supporting 1,024 tokens. The smaller limit applies to that particular bundle, not automatically to every Laya deployment or to the app’s exact build.
Rank #4
- This pre-owned product is not Apple certified, but has been professionally inspected, tested and cleaned by Amazon-qualified suppliers.
- There will be no visible cosmetic imperfections when held at an arm’s length.
- This product is eligible for a replacement or refund within 90 days of receipt if you are not satisfied.
- Product may come in generic Box.
What the available benchmarks do not prove
The Laya project repository reports results on its own typed-decisions benchmark: base checkpoints scored 0.36 and 0.35 against a 0.318 random baseline, while a fine-tuned checkpoint scored 0.766 on the same 2,000 decisions. Those project-reported results concern a separate benchmark. They do not validate relationship judgments in this app, establish general model accuracy, or show that its displayed scores are calibrated probabilities. The repository recommends held-out evaluation for calibration claims.
Windows Errors? Fix Them Before They Spread
Repair common Windows errors and clear accumulated junk for a smoother, more stable PC - no reinstall needed.Free scan · no reinstallCrashes, No Sound, or Screen Glitches?
Random freezes, missing sound and display glitches usually trace back to one bad driver. Find and replace yours safely.Free scan · under a minuteThe maker’s article reports no latency, battery, or accuracy benchmark for the app. It also does not provide measured comparisons across iPhone models. Without those tests, there is no basis to call the app fast, battery-efficient, accurate, or responsive on a particular device.
Best Value
- 6.1" Super Retina XDR OLED, HDR10, 800 nits (HBM), 1200 nits (peak), 2532x1170px at 460ppi, 4005mAh Battery
- 8GB RAM, Apple A18 6-core CPU (2 performance + 4 efficiency cores), Apple GPU 4-core, 16‑core Neural Engine
- Rear camera: 48MP, f/1.6, wide, Front Camera: 12MP, f/1.9, wide, iOS 18.3.1, upgradable to iOS 18.5
- Connectivity: Global 4G LTE, Sub-6 GHz 5G, LTE, Wi-Fi 6, Bluetooth 5.3, NFC, USB-C, Wireless Charging (7.5W). (does not have mmWave 5G or MagSafe or physical SIM card) - Dual eSIM Only
- Unlocked for freedom to choose your carrier. Compatible with both GSM & CDMA networks. The phone is unlocked to work with all GSM Carriers & CDMA Carriers Including AT&T, T-Mobile, Verizon, Straight Talk., Etc.
What a useful app evaluation would need to test
The maker identifies several questions for a reproducible evaluation, rather than reporting them as completed tests:
- Does reversing the order of candidate answers change which one the model prefers?
- Does a neutral paraphrase of the same situation change the result?
- Does adding contradictory details increase uncertainty?
- Do reassuring or negative words dominate otherwise equivalent context?
- Does the interface remain responsive while the model loads and speech transcription runs?
A documented set of cases and repeatable conditions would make those behaviors easier to assess than an unsupported accuracy percentage. For practical deployment comparisons, the relevant measures include the model variant and language coverage, total input limit, storage and memory footprint, first-run download strategy, and device-specific latency, battery use, and interface responsiveness.
Deployment options are not an iPhone compatibility verdict
The deployment documentation describes multiple ways to run Laya, including Core ML on iOS, Python, MLX, Node.js/ONNX, CPU-oriented runtimes, and a local server. The existence of these routes does not show that they perform equally, support the same limits, or have been tested for this app across iPhones. The guides explain implementation options; they are not a verified compatibility matrix or an independent device review.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
