797GB of n-gram counts in CPU RAM let 1B models match 57% more compute
PangWeiKoh · x · 2026-10-15
Ian Magnusson shares an experiment: storing n-gram counts in read-only CPU RAM to help train language models. Scaled to 1B parameters, the approach matches baselines trained with 57% more compute. Others recently broke nanoGPT speedrun records with a similar trick, and this work validates it at larger scale.
More from Models
- Opus 5 might be a very deep model or use looping, commentator speculates — scaling01 · 2026-10-16
- GPT-6.1 Sol audit finds 6% of arXiv papers had false main theorems, down to 1.5% recently — nitarshan · 2026-10-16
- Nvidia-backed post-training pushes Nemotron 3.5 VL past frontier on dermatology diagnosis — LoganGrasby · 2026-10-16
- Gemini 4 Argon scores 97.5% on ARC-AGI-3, second lab above 95% — patience_cave · 2026-10-16
- Microsoft MAI claims SOTA 3T-param in-house base models, post-training results coming — soldni · 2026-10-16
- Datadog's Scout 1.0: post-trained GLM-5.3 Flash matches frontier models for AI SRE at lower cost — Tim_Dettmers · 2026-10-16