Maple-Preview

Narrative intelligence for Maple-Preview: 1 tracked articles, claims, and spin patterns across AI and technology coverage.

SPIN Processed News Frame: The Hype

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

A forum post announces 'Maple-Preview', a claimed ternary 20B MoE (Mixture of Experts) AI model purportedly running at 120 tokens per second on an iPhone, with no technical documentation, benchmark validation, or verifiable evidence provided.

Spin 85% Claim Present in Source AI Risk High

Hacker News Front Page

Aug 5, 2026

Related Claims

01 Maple-Preview is a ternary 20B MoE model running at 120 tokens per second on an iPhone.

Markdown (.md) · JSON-LD schema (.json) · Machine-readable for AI & GEO