Lattice: An 8MB Static Embedding Model that Processes Wikipedia in 7 Minutes
vanstriendaniel · x · 2026-08-08
A developer released Lattice, a highly compact static embedding model. Occupying just 7.94 MB on disk, it can embed the entire English Wikipedia in 7 minutes on an Apple M2 MacBook Air. It achieves a 0.530 NDCG@10 score on the NanoBEIR benchmark. The model, training code, and a detailed blog post have all been made open-source.
More from Models
- Wayve Unveils GAIA-4 World Model: Solving Safety Simulation for Autonomous Driving — alexgkendall · 2026-08-08
- Expert Warns: LLM Math Capabilities Remain Absurdly Jagged — lateinteraction · 2026-08-08
- Rumor: GPT-6 Release Delayed Over 'Critical' Cybersecurity Capabilities — Endonium · 2026-08-08
- Downgrading to Opus 4.8 Because Opus 5.0 Acts Like a Stubborn Senior Scientist — sokrypton · 2026-08-08
- OpenAI Treats Upcoming 'Astra' (GPT-6) as First Critical Cybersecurity Model — Endonium · 2026-08-08
- Testing Claude Opus 5: Great Copy, But Layouts Aren't Client-Ready — yuwen_lu_ · 2026-08-08