{"slug": "google-ai-edge-gallery", "name": "Google AI Edge Gallery", "category": "ai", "category_name": "AI tools and apps", "description": "", "recommenders": 3, "commenters": 5, "warners": 1, "score": 1.991, "rising": -0.98, "first": "2025-12-18", "latest": "2026-07-20", "why": "Check out this app they built which loads in the Gemma 270m models and runs them on your phone.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 1, "compare": 0, "warn": 1}, "spark": [0, 1, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "Check out this app they built which loads in the Gemma 270m models and runs them on your phone.", "kind": "", "icon": true, "domain": null, "github_repo": "github.com/google-ai-edge/gallery", "official_url": "", "pricing": "", "aliases": ["Google AI Edge Gallery"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 768458256, "item_id": 48028641, "url": "https://news.ycombinator.com/item?id=48028641", "by": "nolist_policy", "date": "2026-05-05", "version": null, "stance": "recommend", "quote": "Works great in the latest version of Google AI Edge Gallery", "excerpt": "Works great in the latest version of Google AI Edge Gallery: https://github.com/google-ai-edge/gallery/releases", "context": "", "use_case": "Running Gemma locally", "switched_from": "", "story": "Accelerating Gemma 4: faster inference with multi-token prediction drafters"}, {"id": 762003424, "item_id": 47625214, "url": "https://news.ycombinator.com/item?id=47625214", "by": "swaminarayan", "date": "2026-04-03", "version": null, "stance": "recommend", "quote": "Found my answer: https://github.com/google-ai-edge/gallery?tab=readme-ov-file", "excerpt": "Found my answer: https://github.com/google-ai-edge/gallery?tab=readme-ov-file", "context": "", "use_case": "on-device LLM on Android", "switched_from": "", "story": "Ask HN: Best LLM model for a RAG-based Android app across all smartphones?"}, {"id": 741094689, "item_id": 46318418, "url": "https://news.ycombinator.com/item?id=46318418", "by": "canyon289", "date": "2025-12-18", "version": null, "stance": "recommend", "quote": "Check out this app they built which loads in the Gemma 270m models and runs them on your phone.", "excerpt": "Its already on the phone! Check out the demo videos and colab that show you how to load this model onto a device relatively easily. On this project I was lucky enough to work with the Google AI Edge team who have deep expertise in edge deployments on device. Check out this app they built which loads in the Gemma 270m models and runs them on your phone. https://play.google.com/store/apps/details?id=com.google.ai.edge.", "context": "worked on the FunctionGemma project", "use_case": "running Gemma models on phone", "switched_from": "", "story": "FunctionGemma 270M Model"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 762543888, "item_id": 47658993, "url": "https://news.ycombinator.com/item?id=47658993", "by": "selfsigned", "date": "2026-04-06", "version": null, "stance": "warn", "quote": "they're using firebase-analytics", "excerpt": "Two (very quick) minutes on their GitHub repo and it's pretty obvious that they're using firebase-analytics and at the very least seem to be sending URLs[1] and infos such as the model you download or the capacities[2] you use. [1] https://github.com/google-ai-edge/gallery/blob/main/Android/src/app/src/main/java/com/google/ai/edge/gallery/ui/common/ClickableLink.kt#L62 [2] https://github.com/google-ai-edge/gallery/bl", "context": "", "use_case": "", "switched_from": "", "story": "Gemma 4 on iPhone"}]}], "who": [{"by": "canyon289", "context": "worked on the FunctionGemma project", "url": "https://news.ycombinator.com/item?id=46318418", "date": "2025-12-18"}], "tags": [], "use_cases": ["trying small gemma models", "running gemma locally", "on-device llm on android", "running gemma models on phone"], "compared": [{"slug": "gemma", "name": "Gemma", "co": 3, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=48982681", "title": "Nativ: Run frontier open models locally on your Mac", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48024540", "title": "Accelerating Gemma 4: faster inference with multi-token prediction drafters", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47652561", "title": "Gemma 4 on iPhone", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47624065", "title": "Ask HN: Best LLM model for a RAG-based Android app across all smartphones?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46316533", "title": "FunctionGemma 270M Model", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {"recommend": 1}, "2026-01": {}, "2026-02": {}, "2026-03": {}, "2026-04": {"recommend": 1, "warn": 1}, "2026-05": {"recommend": 1}, "2026-06": {}, "2026-07": {"neutral": 1}, "2026-08": {}, "2026-09": {}, "2026-10": {}}, "versions": [], "version_unnamed": 0, "family_ref": null, "runs_on": null, "lines": [], "quotes": [{"id": 783782146, "item_id": 48986384, "url": "https://news.ycombinator.com/item?id=48986384", "by": "dofm", "date": "2026-07-20", "version": null, "stance": "neutral", "quote": "You can use the Google AI Edge Gallery to play with the smaller Gemma models", "excerpt": "On an M1 Max I have been using either Unsloth Studio (which is basically a web app) or LM Studio (nicer app on the Mac). You can use the Google AI Edge Gallery to play with the smaller Gemma models (but at the moment the QAT variants don't seem to be there unless I am missing something). I think it's likely the 26B QAT model won't fit in your machine \u2014 you may be able to fit one of the UD_Q3 or UD_Q2 variants but whe", "context": "", "use_case": "trying small Gemma models", "switched_from": "", "story": "Nativ: Run frontier open models locally on your Mac"}, {"id": 768458256, "item_id": 48028641, "url": "https://news.ycombinator.com/item?id=48028641", "by": "nolist_policy", "date": "2026-05-05", "version": null, "stance": "recommend", "quote": "Works great in the latest version of Google AI Edge Gallery", "excerpt": "Works great in the latest version of Google AI Edge Gallery: https://github.com/google-ai-edge/gallery/releases", "context": "", "use_case": "Running Gemma locally", "switched_from": "", "story": "Accelerating Gemma 4: faster inference with multi-token prediction drafters"}, {"id": 762543888, "item_id": 47658993, "url": "https://news.ycombinator.com/item?id=47658993", "by": "selfsigned", "date": "2026-04-06", "version": null, "stance": "warn", "quote": "they're using firebase-analytics", "excerpt": "Two (very quick) minutes on their GitHub repo and it's pretty obvious that they're using firebase-analytics and at the very least seem to be sending URLs[1] and infos such as the model you download or the capacities[2] you use. [1] https://github.com/google-ai-edge/gallery/blob/main/Android/src/app/src/main/java/com/google/ai/edge/gallery/ui/common/ClickableLink.kt#L62 [2] https://github.com/google-ai-edge/gallery/bl", "context": "", "use_case": "", "switched_from": "", "story": "Gemma 4 on iPhone"}, {"id": 762003424, "item_id": 47625214, "url": "https://news.ycombinator.com/item?id=47625214", "by": "swaminarayan", "date": "2026-04-03", "version": null, "stance": "recommend", "quote": "Found my answer: https://github.com/google-ai-edge/gallery?tab=readme-ov-file", "excerpt": "Found my answer: https://github.com/google-ai-edge/gallery?tab=readme-ov-file", "context": "", "use_case": "on-device LLM on Android", "switched_from": "", "story": "Ask HN: Best LLM model for a RAG-based Android app across all smartphones?"}, {"id": 741094689, "item_id": 46318418, "url": "https://news.ycombinator.com/item?id=46318418", "by": "canyon289", "date": "2025-12-18", "version": null, "stance": "recommend", "quote": "Check out this app they built which loads in the Gemma 270m models and runs them on your phone.", "excerpt": "Its already on the phone! Check out the demo videos and colab that show you how to load this model onto a device relatively easily. On this project I was lucky enough to work with the Google AI Edge team who have deep expertise in edge deployments on device. Check out this app they built which loads in the Gemma 270m models and runs them on your phone. https://play.google.com/store/apps/details?id=com.google.ai.edge.", "context": "worked on the FunctionGemma project", "use_case": "running Gemma models on phone", "switched_from": "", "story": "FunctionGemma 270M Model"}]}