PulseAugur
EN
LIVE 19:48:54

20B MoE AI Model Runs at 120 Tokens/Sec on iPhone

By PulseAugur Editorial · [3 sources] ·

A new demonstration, Maple-Preview, showcases a 20-billion parameter Mixture-of-Experts (MoE) model capable of running at 120 tokens per second on an iPhone. This development highlights the increasing efficiency and on-device capabilities of large language models. AI

IMPACT Demonstrates significant progress in on-device AI processing, potentially enabling more powerful mobile applications.

RANK_REASON Demonstration of a model running on consumer hardware, not a new model release from a frontier lab.

Read on Hacker News — AI stories ≥50 points →

AI-generated summary · Google Gemini · from 3 sources. How we write summaries →

20B MoE AI Model Runs at 120 Tokens/Sec on iPhone

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Demonstration of a model running on consumer hardware, not a new model release from a frontier lab.
Source corroboration
3 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
model release, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
53 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+1 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

Full methodology in our editorial standards.

COVERAGE [3]

  1. Hacker News — AI stories ≥50 points TIER_1 English(EN) · edwardbzhang ·

    Show HN: Maple-Preview – ternary 20B MoE running at 120 tok/s on a iPhone

  2. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    Show HN: Maple-Preview – ternary 20B MoE running at 120 tok/s on a iPhone https:// deepgrove.ai/maple-preview # ai # iphone

    Show HN: Maple-Preview – ternary 20B MoE running at 120 tok/s on a iPhone https:// deepgrove.ai/maple-preview # ai # iphone

  3. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    Show HN: Maple-Preview – ternary 20B MoE running at 120 tok/s on a iPhone Article URL: https:// deepgrove.ai/maple-preview Comments URL: https:// news.ycombinat

    Show HN: Maple-Preview – ternary 20B MoE running at 120 tok/s on a iPhone Article URL: https:// deepgrove.ai/maple-preview Comments URL: https:// news.ycombinator.com/item?id=4 9173984 Points: 9 # Comments: 4 https:// deepgrove.ai/maple-preview # Tech # Technology # TechNews # AI…

RELATED ENTITIES

RELATED TOPICS