The demand for mobile proving is increasing across the industry, driven by applications in ZK identity, anonymous online collaboration, and voting. Some examples of such applications are Anon Aadhaar and zkEmail. They involve computationally intensive client-side proving, primarily due to the need to prove conventional, ZK-unfriendly cryptography (ECDSA signature verification, SHA-256 hashing) coming from credential issuers.
Projects like mopro have made significant progress in optimizing existing ZK frameworks for mobile use. Traditionally, benchmarking efforts have focused on measuring performance improvements relative to unoptimized versions, independent of hardware (e.g., comparing a native binary to a WASM/JS prover running in a mobile browser).
The upcoming client-side proving research project within PSE aims to implement ZK proving systems on mobile that are particularly well-suited for client-side proving. Understanding mobile platforms' limitations is crucial to determining a range of suitable proving systems and frameworks.
This survey aims to determine the most average consumer mobile hardware globally to serve as a reference for benchmarking purposes.
Comprehensive market reports from research firms such as IDC and Counterpoint are prohibitively expensive (e.g., $7500), making them inaccessible for this analysis.
We analyzed the data published by various mobile SDK developers in different industries (analytics, gaming, ads). We deliberately discarded the "best selling phone" press articles and other market reports as they do not reflect the actual device usage statistics.
Android is dominating the market, while the iPhone's share is around 27%.
The table[1] below contains the hardware specs[2] of ten most popular iPhone devices from the TelemetryDeck survey:
iPhone model | Market share | CPU Cores | Max CPU Freq, MHz | RAM, GB |
---|---|---|---|---|
iPhone 11 | 11.04% | 6 | 2650 | 4 |
iPhone 12 | 8.50% | 6 | 3100 | 4 |
iPhone 13 | 16.30% | 6 | 3230 | 4 |
iPhone 13 Pro Max | 7.19% | 6 | 3230 | 6 |
iPhone 14 | 10.14% | 6 | 3230 | 6 |
iPhone 14 Pro | 8.82% | 6 | 3460 | 6 |
iPhone 14 Pro Max | 8.39% | 6 | 3460 | 6 |
iPhone 15 | 8.71% | 6 | 3460 | 6 |
iPhone 15 Pro | 10.19% | 6 | 3780 | 8 |
iPhone 15 Pro Max | 10.70% | 6 | 3780 | 8 |
Weighted Avg | 6 | 3,329.40 | 5.70 |
Android phone model | Market share | CPU Cores | Max CPU Freq, MHz | AnTuTu bench v8 | GeekBench v5.1 | RAM, min GB | RAM, max GB |
---|---|---|---|---|---|---|---|
Samsung Galaxy A12 | 1.50% | 8 | 2350 | 107189 | 1034 | 2 | 6 |
Samsung Galaxy A13 | 1.10% | 8 | 2000 | 122822 | 588 | 3 | 6 |
Samsung Galaxy A32 | 0.70% | 8 | 2000 | 286666 | 1277 | 4 | 8 |
Samsung Galaxy A15 | 0.70% | 8 | 2200 | - | - | 4 | 8 |
Samsung Galaxy A14 | 0.70% | 8 | 2000 | - | - | 4 | 6 |
Samsung Galaxy A54 5G | 0.70% | 8 | 2400 | - | 2703 | 4 | 8 |
Samsung Galaxy A21s | 0.60% | 8 | 2000 | 107157 | 1100 | 2 | 6 |
Samsung Galaxy S23 Ultra | 0.60% | 8 | 2800 | - | 4927 | 8 | 12 |
Samsung Galaxy A51 | 0.60% | 8 | 2300 | 175363 | 1294 | 4 | 8 |
Samsung Galaxy S24 Ultra | 0.60% | 8 | 3390 | - | - | 12 | 12 |
Weighted Average | 8 | 2,312.69 | 148,014.64 | 1,616.62 | 4.24 | 7.62 |
Android phone model | CPU Cores | Max CPU Freq, MHz | RAM, min GB | RAM, max GB |
---|---|---|---|---|
Samsung Galaxy J7 | 8 | 1500 | 1.5 | 1.5 |
Samsung Galaxy S7 Edge | 8 (latest), 4 (initial) | 2300 | 4 | 4 |
Google Pixel 3A | 8 | 2000 | 4 | 4 |
Samsung Galaxy J5 Prime | 4 | 1400 | 2 | 2 |
Samsung Galaxy A7 | 8 | 2200 | 4 | 6 |
Samsung Galaxy J5 | 4 | 1200 | 1.5 | 1.5 |
Samsung Galaxy A12 | 8 | 2350 | 2 | 6 |
Samsung Galaxy S22 | 8 | 2800 | 8 | 8 |
Huawei Mate 10 Lite | 8 | 2360 | 4 | 4 |
Samsung Galaxy A5 | 8 | 1900 | 3 | 3 |
Average | 7.00 | 2,001.00 | 3.40 | 4.00 |
Calculations: https://docs.google.com/spreadsheets/d/1rT-anOj7O7ixElRMsbyFV5Of7L35DIOzAtInD-lG4mw/edit?usp=sharing ↩︎ ↩︎ ↩︎
The hardware specs are taken from https://www.gsmarena.com/ ↩︎ ↩︎ ↩︎
AFTMM is the build model for the first generation of the Amazon Fire TV Stick 4K ↩︎