{"slug": "locally-ai", "name": "Locally AI", "category": "ai", "category_name": "AI tools and apps", "description": "", "recommenders": 3, "commenters": 6, "warners": 0, "score": 3.585, "rising": 0.02, "first": "2026-03-31", "latest": "2026-10-17", "why": "I\u2019d recommend locally.ai[1] - it\u2019s really good and has a wide range of models", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 4, "neutral": 3, "compare": 0, "warn": 0}, "spark": [0, 0, 0, 0, 1, 2, 0, 0, 0, 0, 0, 1], "listed": true, "loved": [], "caveat": "", "short_quote": "I\u2019d recommend locally.ai[1] - it\u2019s really good and has a wide range of models", "kind": "", "icon": true, "domain": "locallyai.app", "github_repo": null, "official_url": "https://locallyai.app/", "pricing": "", "aliases": ["Locally AI"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 802143872, "item_id": 50133992, "url": "https://news.ycombinator.com/item?id=50133992", "by": "simonw", "date": "2026-10-17", "version": null, "stance": "recommend", "quote": "My current favorite is this one", "excerpt": "My current favorite is this one: https://apps.apple.com/us/app/locally-ai-by-lm-studio/id6741426692 It's free, not annoying, and has a bunch of model options.", "context": "", "use_case": "running local models on iPhone", "switched_from": "", "story": "Qwen3.8-27B on the iPhone 18 Neural Engine at 15\u201370 tok/s (1.5 bpw)"}, {"id": 762551312, "item_id": 47659457, "url": "https://news.ycombinator.com/item?id=47659457", "by": "janandonly", "date": "2026-04-06", "version": null, "stance": "recommend", "quote": "This app unlocks using the Apple Foundation model itself", "excerpt": "This app unlocks using the Apple Foundation model itself: https://apps.apple.com/nl/app/locally-ai-local-ai-chat/id6741426692", "context": "", "use_case": "on-device AI chat", "switched_from": "", "story": "Gemma 4 on iPhone"}, {"id": 762543824, "item_id": 47658989, "url": "https://news.ycombinator.com/item?id=47658989", "by": "orf", "date": "2026-04-06", "version": null, "stance": "recommend", "quote": "I\u2019d recommend locally.ai[1] - it\u2019s really good and has a wide range of models", "excerpt": "I\u2019d recommend locally.ai[1] - it\u2019s really good and has a wide range of models. Also has shortcuts support. 1. https://apps.apple.com/gb/app/locally-ai-local-ai-chat/id6741426692", "context": "", "use_case": "", "switched_from": "", "story": "Gemma 4 on iPhone"}, {"id": 761549712, "item_id": 47596857, "url": "https://news.ycombinator.com/item?id=47596857", "by": "simonw", "date": "2026-03-31", "version": null, "stance": "recommend", "quote": "You can run this model on an iPhone via the latest update to this Locally AI app", "excerpt": "You can run this model on an iPhone via the latest update to this Locally AI app: https://apps.apple.com/us/app/locally-ai-local-ai-chat/id6741426692 For its size (1.2GB download) it's very impressive. Here's a pelican it drew me running on my phone - the SVG comments are good, the image not so much: https://tools.simonwillison.net/svg-render#%3Csvg%20width%3D%22500%22%20height%3D%22300%22%20viewBox%3D%220%200%20500%", "context": "", "use_case": "running local models on iPhone", "switched_from": "", "story": "Show HN: 1-Bit Bonsai, the First Commercially Viable 1-Bit LLMs"}]}], "caveats": [], "who": [], "tags": [], "use_cases": ["running local models on iphone", "on-device ai chat", "on-device model runner"], "compared": [], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=47652561", "title": "Gemma 4 on iPhone", "mentions": 3}, {"url": "https://news.ycombinator.com/item?id=50133500", "title": "Qwen3.8-27B on the iPhone 18 Neural Engine at 15\u201370 tok/s (1.5 bpw)", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=48910545", "title": "Bonsai 27B (1-bit LLM): The First 27B-Class Model to Run on a Phone", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47593422", "title": "Show HN: 1-Bit Bonsai, the First Commercially Viable 1-Bit LLMs", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {"recommend": 1}, "2026-04": {"neutral": 1, "recommend": 2}, "2026-05": {}, "2026-06": {}, "2026-07": {"neutral": 1}, "2026-08": {}, "2026-09": {}, "2026-10": {"recommend": 1, "neutral": 1}}, "versions": [], "version_unnamed": 0, "family_ref": null, "runs_on": null, "lines": [], "quotes": [{"id": 802145120, "item_id": 50134070, "url": "https://news.ycombinator.com/item?id=50134070", "by": "layer8", "date": "2026-10-17", "version": null, "stance": "neutral", "quote": "Non-app-store link: https://locallyai.app/", "excerpt": "Non-app-store link: https://locallyai.app/ However this uses the GPU, not the Neural Engine like the submission.", "context": "", "use_case": "", "switched_from": "", "story": "Qwen3.8-27B on the iPhone 18 Neural Engine at 15\u201370 tok/s (1.5 bpw)"}, {"id": 802143872, "item_id": 50133992, "url": "https://news.ycombinator.com/item?id=50133992", "by": "simonw", "date": "2026-10-17", "version": null, "stance": "recommend", "quote": "My current favorite is this one", "excerpt": "My current favorite is this one: https://apps.apple.com/us/app/locally-ai-by-lm-studio/id6741426692 It's free, not annoying, and has a bunch of model options.", "context": "", "use_case": "running local models on iPhone", "switched_from": "", "story": "Qwen3.8-27B on the iPhone 18 Neural Engine at 15\u201370 tok/s (1.5 bpw)"}, {"id": 782614480, "item_id": 48913405, "url": "https://news.ycombinator.com/item?id=48913405", "by": "smallerize", "date": "2026-07-14", "version": null, "stance": "neutral", "quote": "it requires an iPhone 17 Pro or Pro Max to run the 27B model", "excerpt": "One of the links on the sidebar goes to \"Locally AI\" https://apps.apple.com/us/app/locally-ai-by-lm-studio/id6741426692 it requires an iPhone 17 Pro or Pro Max to run the 27B model though.", "context": "", "use_case": "", "switched_from": "", "story": "Bonsai 27B (1-bit LLM): The First 27B-Class Model to Run on a Phone"}, {"id": 762551312, "item_id": 47659457, "url": "https://news.ycombinator.com/item?id=47659457", "by": "janandonly", "date": "2026-04-06", "version": null, "stance": "recommend", "quote": "This app unlocks using the Apple Foundation model itself", "excerpt": "This app unlocks using the Apple Foundation model itself: https://apps.apple.com/nl/app/locally-ai-local-ai-chat/id6741426692", "context": "", "use_case": "on-device AI chat", "switched_from": "", "story": "Gemma 4 on iPhone"}, {"id": 762543824, "item_id": 47658989, "url": "https://news.ycombinator.com/item?id=47658989", "by": "orf", "date": "2026-04-06", "version": null, "stance": "recommend", "quote": "I\u2019d recommend locally.ai[1] - it\u2019s really good and has a wide range of models", "excerpt": "I\u2019d recommend locally.ai[1] - it\u2019s really good and has a wide range of models. Also has shortcuts support. 1. https://apps.apple.com/gb/app/locally-ai-local-ai-chat/id6741426692", "context": "", "use_case": "", "switched_from": "", "story": "Gemma 4 on iPhone"}, {"id": 762509281, "item_id": 47656830, "url": "https://news.ycombinator.com/item?id=47656830", "by": "MysticOracle", "date": "2026-04-05", "version": null, "stance": "neutral", "quote": "Locally AI - https://locallyai.app/", "excerpt": "Crashes for me on a couple of different iDevices (2 generations behind) after only a few 2-3 chats. Probably not enough RAM. Saw this one on X the other day updated with Gemma 4 and they have the built-in Apple Foundation model, Qwen3.5, and other models: Locally AI - https://locallyai.app/", "context": "", "use_case": "On-device model runner", "switched_from": "", "story": "Gemma 4 on iPhone"}, {"id": 761549712, "item_id": 47596857, "url": "https://news.ycombinator.com/item?id=47596857", "by": "simonw", "date": "2026-03-31", "version": null, "stance": "recommend", "quote": "You can run this model on an iPhone via the latest update to this Locally AI app", "excerpt": "You can run this model on an iPhone via the latest update to this Locally AI app: https://apps.apple.com/us/app/locally-ai-local-ai-chat/id6741426692 For its size (1.2GB download) it's very impressive. Here's a pelican it drew me running on my phone - the SVG comments are good, the image not so much: https://tools.simonwillison.net/svg-render#%3Csvg%20width%3D%22500%22%20height%3D%22300%22%20viewBox%3D%220%200%20500%", "context": "", "use_case": "running local models on iPhone", "switched_from": "", "story": "Show HN: 1-Bit Bonsai, the First Commercially Viable 1-Bit LLMs"}]}