{"rewrite":{"id":"r_aa2c8ecb5f4ae259ca5eb53a","clusterId":"c_79e1f162eab196632bb7f014","slug":"prismml-compresses-27b-parameter-ai-model-to-run-on-iphone-17-pro","model":"deepseek-v4-flash","headline":"PrismML Compresses 27B-Parameter AI Model to Run on iPhone 17 Pro","summary":"AI developer PrismML claims to have compressed Alibaba's 27-billion-parameter Qwen3.6-27B model to under 4GB and run it on an iPhone 17 Pro with all parameters active. Apple has held a meeting with PrismML to discuss using the compression technology. PrismML's 1-bit Bonsai method reduces memory and computation. The compressed model is planned for open source release on July 14, 2026.","whyItMatters":"If PrismML's compression proves practical, Apple could run large dense AI models entirely on-device, reducing server costs and improving privacy without relying on cloud processing.","webCardHtml":"\u003cp\u003ePrismML\u0026#39;s 1-bit Bonsai method represents each weight with a single bit, cutting memory usage by up to 1/14 compared to standard 16-bit models. The company claims it compressed the approximately 54 GB Qwen3.6-27B to under 4 GB while keeping all 27 billion parameters active. Apple\u0026#39;s current on-device model, AFM 3 Core Advanced, uses a sparse architecture that activates only 1 to 4 billion parameters at a time. Apple has reportedly met with PrismML to discuss integrating the technology into iPhones. PrismML plans to release the compressed model as open source on July 14.\u003c/p\u003e","blueskyPost":"PrismML claims to have compressed Alibaba's 27B-parameter Qwen3.6-27B model to under 4GB and run it on an iPhone 17 Pro. Apple has reportedly discussed using the technology. The compressed model is set for open source release on July 14.","twitterPost":"PrismML says it compressed a 27B-parameter AI model to under 4GB and ran it on an iPhone 17 Pro. Apple held a meeting about the tech. Open source release planned for July 14.","threadsPost":null,"newsletterBlurb":"PrismML claims to have compressed Alibaba's 27-billion-parameter Qwen3.6-27B model to run on an iPhone 17 Pro. Apple has reportedly discussed using the compression technology. The company plans to release the compressed model as open source on July 14.","attributionJson":"[{\"source\":\"GIGAZINE\",\"url\":\"https://gigazine.net/news/20260710-prismml-iphone-apple-qwen/\",\"title\":\"AI 'Qwen3.6-27B' with 27 billion parameters runs on iPhone 17 Pro, Apple reportedly discussing use of compression technology with PrismML\"}]","lintFlagsJson":null,"lintHits":0,"costUsd":0,"inputTokens":4119,"outputTokens":2201,"status":"published","repairAttempts":0,"nextRepairAt":null,"factsAttemptedAt":1783756063,"createdAt":"2026-07-11T07:38:31.000Z","publishedAt":"2026-07-11T07:42:28.000Z","updatedAt":"2026-07-11T07:38:31.000Z"},"cluster":{"id":"c_79e1f162eab196632bb7f014","canonicalTitle":"iPhone 17 Proで270億パラメータのAI「Qwen3.6-27B」が動作、AppleはPrismMLと圧縮技術の活用を協議か","representativeArticleId":"a_6d9d2b6228a272d7e6200e8f","sourceCount":1,"writtenSourceCount":1,"writeAttempts":0,"isSolo":true,"entitiesJson":"{\"anime_titles\":[],\"manga_titles\":[],\"work_titles\":[],\"studios\":[],\"people\":[],\"type\":\"news\",\"domain\":\"other\",\"is_roundup\":false}","contentType":"news","status":"published","firstSeenAt":"2026-07-10T06:10:00.000Z","lastSeenAt":"2026-07-10T06:10:00.000Z","updatedAt":"2026-07-11T07:42:29.000Z"},"attribution":[{"source":"GIGAZINE","url":"https://gigazine.net/news/20260710-prismml-iphone-apple-qwen/","title":"iPhone 17 Proで270億パラメータのAI「Qwen3.6-27B」が動作、AppleはPrismMLと圧縮技術の活用を協議か"}],"entities":{"anime_titles":[],"manga_titles":[],"work_titles":[],"studios":[],"people":[],"type":"news","domain":"other","is_roundup":false},"keyFacts":null}