Google AI Edge Gallery vs G
Price, ratings, monetisation and update history for both apps, side by side — with what reviewers say about each.
Google AI Edge Gallery
Run powerful open-source AI models directly on your mobile device. Experience generative AI offline, privately, and with high performance. Explore features like agent skills, AI chat with reasoning visualization, and image/audio analysis.
- On-device LLM execution
- Agent skills for proactive assistance
- AI chat with reasoning visualization
- Multimodal image analysis
- Real-time audio transcription and translation
- Prompt testing and model parameter control
- Offline device control and automation
Read full descriptionHide full description
AI Edge Gallery is the premier destination for running the world’s most powerful open-source Large Language Models (LLMs) on your mobile device. Experience high-performance Generative AI directly on your hardware—fully offline, private, and lightning-fast. Now Featuring: EmbeddingGemma 2 This update brings official support for the newly released EmbeddingGemma 2 model. With this release, we bring cutting edge, multimodal semantic search running 100% on your device. Try out these new capabilities in our new features Instant Media Search and Video Moment Finder. Core Features - Agent Skills: Transform your LLM from a conversationalist into a proactive assistant. Use the Agent Skills tile to augment model capabilities with tools like Wikipedia for fact-grounding, interactive maps, and rich visual summary cards. You can even load modular skills from a URL or browse community contributions on GitHub Discussions. - AI Chat with Thinking Mode: Engage in fluid, multi-turn conversations and toggle the new Thinking Mode to peek "under the hood." This feature allows you to see the model’s step-by-step reasoning process, which is perfect for understanding complex problem-solving. Note: Thinking Mode currently works with supported models, starting with the Gemma 4 family. - Instant Media Search: Explore your photo library (or built-in sample media) with fast, search-as-you-type natural language queries and image-to-image similarity matching—with zero cloud roundtrips. - Video Moment Finder: Pinpoint exact moments inside videos using natural language descriptions. Jump straight to highlighted timestamps on an interactive timeline, trim clips, and save or export your favorite moments - Ask Image: Use multimodal power to identify objects, solve visual puzzles, or get detailed descriptions using your device’s camera or photo gallery. - Audio Scribe: Transcribe and translate voice recordings into text in real-time using high-efficiency on-device language models. - Prompt Lab: A dedicated workspace to test different prompts and single-turn use cases with granular control over model parameters like temperature and top-k. - Mobile Actions: Unlock offline device controls and automated tasks powered entirely by a finetune of FuntionGemma 270m. - Tiny Garden: A fun, experimental mini-game that uses natural language to plant and harvest a virtual garden using a finetune of FunctionGemma 270m. - Model Management & Benchmark: Gallery is a flexible sandbox for a wide variety of open-source models. Easily download models from the list or load your own custom models. Manage your model library effortlessly and run benchmark tests to understand exactly how each model performs on your specific hardware. - 100% On-Device Privacy: All model inferences happen directly on your device hardware. No internet is required, ensuring total privacy for your prompts, images, and sensitive data. Built for the Community AI Edge Gallery is an open-source project designed for the developer community and AI enthusiasts alike. Explore our example features, contribute your own skills, and help shape the future of the on-device agent ecosystem. Check out the source code on GitHub: https://github.com/google-ai-edge/gallery Note: This app is in active development. Performance is dependent on your device's hardware (CPU/GPU). For support or feedback, contact us at google-ai-edge-gallery-android-feedback@google.com.
G
Measure real-time G-forces on three axes with a precision crosshair display. Track peak G, acceleration history, and impact forces. Ideal for car performance, roller coasters, aviation, and physics experiments.
- 3-axis G-force tracking
- Precision crosshair display
- Peak G detection
- Real-time chart recording
- G-force level guide
- Adjustable sensitivity
Read full descriptionHide full description
G-Force Meter+ Accelerometer shows the G-force your phone feels right now on every axis, then turns each drive, ride or run into a result you can read: press Start, press Stop, and a session card shows the peak G, the average G and how hard you cornered, accelerated and braked. ▶ Live G-force on every axis • Total G on a round gauge with a moving dot for the direction of the force • Lateral (X), longitudinal (Y) and vertical (Z) values side by side • Min, average, max and peak while you record, plus peak chips for lateral, accel and brake • A scrolling chart of X, Y, Z and total G, or a sentence that explains the current G level ▶ Stop and see the session Press Stop and a Session result card appears: • Duration, peak G and average G • Peak lateral, peak accel and peak brake • A second-by-second G trend line (the first 10 minutes of a session) • With the Car activity selected, a plain-language reading of the drive, from Gentle to Very hard, based on the peak horizontal G Every finished session is saved to History automatically (the last 20). A session shorter than 2 seconds is not saved. If you switch apps mid-session, recording pauses in the background and the same session resumes when you return, and a session cut off when the system closes the app is recovered into History on the next launch. Share a result as text in one tap. ▶ History and personal bests Open History from the top of the Meter screen: personal bests, every session with its G trend, your race runs and rolling runs. Export sessions, runs or rolling intervals as CSV. A statistics report CSV unlocks for 24 hours after a short ad. ▶ G-G friction circle A dedicated tab plots lateral against longitudinal G as a trail inside rings at 0.5, 1.0 and 1.5 G, with peak lateral, longitudinal and combined G, so you can see how much grip you used in corners and under braking. ▶ Race mode • 0-60 mph launch timing with raw and rollout times • 60-0 mph brake test with time, distance and speed shed, estimated from the motion sensors • Rolling intervals: 60-120 mph, 100-200 km/h, 30-50 mph or your own range • GPS cross-check with a GPS 0-60 time, a quarter mile time and trap speed. A good fix shows a GPS-verified badge, otherwise the result is labelled as a sensor estimate • Regen profile for electric cars: braking events sorted by their strength into likely regen (gentle) and likely friction (hard), with their maximum G ▶ Set up for your car • Dash or Holder mount, auto-level and Re-level now • Reference 1G (resting reads 1.00 G) or 0G (resting reads 0.00 G) • Display sensitivity from 0.5x to 2.0x for the live gauge; the result card always shows the true values • Activity presets for Car, Roller-coaster, Sport, Elevator and Aircraft explain what each G level means there • A Guide tab with 8 tips on mounting, reading each axis and typical G in daily life • The screen stays on while recording • Interface in 30 languages ▶ Good to know Readings come from the phone's motion sensor, so mount the phone firmly and level it before you record. Launch and braking times are estimates unless they carry the GPS-verified badge. Only drive-test where it is safe and legal. For drivers checking how smooth or hard they drive, track-day and drag-strip fans, roller-coaster riders, and students who want to see physics in numbers.
Screenshots
Verdict
The clearest difference is ads: Google AI Edge Gallery at none against G's shown. Google AI Edge Gallery also leads on ratings volume (161 vs 3) and rating (4.0 vs 3.7). G's advantage is update cadence (every 4 days vs every 2 weeks). On price, in-app purchases, device support and iOS requirement there is nothing between them.
Scored on Price · Rating · Positive reviews · Number of ratings · Update frequency · Ads · In-app purchases · Monetization · Best chart rank · Devices · Requires iOS
Both are free to download. Neither carries in-app purchases, so what you see is what you pay.
Google AI Edge Gallery holds the better App Store score, 4.0 against 3.7. That said, the two scores are not equally well evidenced: Google AI Edge Gallery has 161 ratings behind it against 3, so its average is the more settled of the two.
Google AI Edge Gallery ships an update every 2 weeks, G every 4 days. The most recent releases landed on October 15, 2026 and October 16, 2026 respectively.
| Parameter | Google AI Edge Gallery | G |
|---|---|---|
| Price | Free | Free |
| Rating | 4.0 (161 ratings) — better | 3.7 (3 ratings) |
| Positive reviews | 58.8% of reviews | — |
| Number of ratings | 161 — better | 3 |
| Update frequency | Every 2 weeks | Every 4 days — better |
| Ads | No — better | Yes |
| In-app purchases | No | No |
| Monetization | Free — better | Ad-supported |
| Devices | iPhone | iPhone |
| Requires iOS | 17.0 | 16.4 — better |
| Further details — not scored | ||
| Size | 134 MB | 53 MB |
| Age rating | 12+ | 17+ |
| Developer | Kyu-Hee Jang | |
Customer experience
Google AI Edge Gallery
G
In-app purchases
Google AI Edge Gallery
No in-app purchases
G
No in-app purchases









