Skip to content
∑ Praveen T N AI & ML
Concepts Flashcards Writing Editorial AI Feed Graph
Portfolio ↗
Overview Concepts Flashcards Writing Editorial AI Feed Graph Search Back to portfolio ↗
AI & ML/ Writing/Tagged “on-device”

Tagged “on-device”

1 posts.

Clear
All Model Architecture19 Training & Alignment22 Inference & Serving20 Agents & Orchestration11 Reasoning & Evaluation27 Safety, Security & Governance7 Platforms & Practice21
Inference & Serving 28 min

One Training Run, Many Models: How Elastic Architectures Replaced the Model Family

The Llama 3 family cost 39.3 million H100 hours across three sizes that were trained three times. Elastic architectures train the largest model once and slice the rest out of its weights at deployment, and by 2026 the technique h…

architecture efficiency inference on-device ∑ ◫
The library

1035 concepts, 11,231 flashcards and 127 long-form pieces on AI, NLP, deep learning, LLMs and agentic systems. Free, no sign-up, no paywall.

Sections Concepts Flashcards Writing AI Feed Knowledge Graph
Elsewhere Portfolio Architecture Practice RSS LinkedIn Buy me a coffee

Written and maintained by Praveen T N.

© 2026 Praveen T N