--- title: Why Large? Tiny LMs & Agents on Edge/Robotics — Cormac... description: A Google AI Edge team tech lead presents the state of tiny language models for edge devices and robotics. The talk covers why edge AI matters (latency,... canonical: https://daily.dev/posts/why-large-tiny-lms-agents-on-edge-robotics-cormac-brick-google-mfv1cywru twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Why Large? Tiny LMs & Agents on Edge/Robotics — Cormac Brick, Google | daily.dev og:description: A Google AI Edge team tech lead presents the state of tiny language models for edge devices and robotics. The talk covers why edge AI matters (latency,... og:url: https://daily.dev/posts/why-large-tiny-lms-agents-on-edge-robotics-cormac-brick-google-mfv1cywru og:image: https://api.daily.dev/og/posts/mFV1cYwru.png og:image:alt: Why Large? Tiny LMs & Agents on Edge/Robotics — Cormac Brick, Google og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Why Large? Tiny LMs & Agents on Edge/Robotics — Cormac Brick, Google **[AI Engineer](https://daily.dev/sources/aidotengineer)** · 21 min read · 0 upvotes · 0 comments ## Summary A Google AI Edge team tech lead presents the state of tiny language models for edge devices and robotics. The talk covers why edge AI matters (latency, privacy, cost savings), the constraints of deploying models on low-RAM devices, and a practical playbook for using small (1–4B parameter) and tiny (50M–500M parameter) models. Key topics include quantization techniques to minimize memory footprint, benchmarks on Raspberry Pi, Jetson Nano, and Qualcomm IoT boards, off-the-shelf fixed-task models for ASR and vision, and fine-tuning tiny models using synthetically generated datasets (10K–10M samples). Real-world examples include a voice-to-function-calling mobile actions model at 86%+ reliability and an offline voice dictation iOS app built on fine-tuned Gemma models in the low hundreds of millions of parameters. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Small Language Models Power Life-Saving Small AI](https://daily.dev/posts/small-language-models-power-life-saving-small-ai-wg2czk7v9) · IEEE Spectrum · 0 upvotes · 0 comments --- Tags: [#data-science](https://daily.dev/tags/data-science), [#deep-learning](https://daily.dev/tags/deep-learning), [#gemma](https://daily.dev/tags/gemma), [#edge-ai](https://daily.dev/tags/edge-ai) [View this post on daily.dev](https://daily.dev/posts/why-large-tiny-lms-agents-on-edge-robotics-cormac-brick-google-mfv1cywru) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Why Large? Tiny LMs & Agents on Edge/Robotics — Cormac Brick, Google","url":"https://daily.dev/posts/why-large-tiny-lms-agents-on-edge-robotics-cormac-brick-google-mfv1cywru","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/why-large-tiny-lms-agents-on-edge-robotics-cormac-brick-google-mfv1cywru"},"datePublished":"2026-07-25T17:03:49.860Z","dateModified":"2026-07-25T17:29:36.255Z","description":"A Google AI Edge team tech lead presents the state of tiny language models for edge devices and robotics. The talk covers why edge AI matters (latency,...","image":"https://i.ytimg.com/vi/hacEQHHhu2Q/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/hacEQHHhu2Q/sddefault.jpg","isAccessibleForFree":true,"articleSection":"AI Engineer","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"AI Engineer","logo":"https://media.daily.dev/image/upload/s--u5PucxNT--/f_auto/v1724338940/logos/aidotengineer","url":"https://daily.dev/sources/aidotengineer"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/why-large-tiny-lms-agents-on-edge-robotics-cormac-brick-google-mfv1cywru","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"data-science,deep-learning,gemma,edge-ai","timeRequired":"PT21M","video":{"@type":"VideoObject","name":"Why Large? Tiny LMs & Agents on Edge/Robotics — Cormac Brick, Google","description":"A Google AI Edge team tech lead presents the state of tiny language models for edge devices and robotics. The talk covers why edge AI matters (latency,...","thumbnailUrl":"https://i.ytimg.com/vi/hacEQHHhu2Q/sddefault.jpg","uploadDate":"2026-07-25T17:03:49.860Z","duration":"PT21M","url":"https://api.daily.dev/r/mFV1cYwru","embedUrl":"https://www.youtube.com/embed/hacEQHHhu2Q"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AI Engineer","item":"https://daily.dev/sources/aidotengineer"},{"@type":"ListItem","position":3,"name":"Why Large? Tiny LMs & Agents on Edge/Robotics — Cormac Brick, Google"}]} ```