Skip to content
∑ Praveen T N Learning Library
Overview Concepts Flashcards Writing AI Feed Graph
Portfolio ↗
Overview Concepts Flashcards Writing AI Feed Graph Search Back to portfolio ↗
Library/ Writing/Tagged “fp4”

Tagged “fp4”

1 posts.

Clear
All Model Architecture13 Training & Alignment8 Inference & Serving11 Agents & Orchestration10 Reasoning & Evaluation7 Safety, Security & Governance3 Platforms & Practice11
Inference & Serving 21 min

Four Bits Per Weight: How Low-Precision Quantization Stopped Hurting LLMs

A 70B model in FP16 needs 140 GB of memory it spends most of its time waiting to read. Dropping each weight to four bits cuts that to 35 GB, and for years that cut also broke the model. Here is what changed.

quantization inference gptq awq ∑ ◫
The library

446 concepts, 2,671 flashcards and 63 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 RSS LinkedIn Buy me a coffee

Written and maintained by Praveen T N.

© 2026 Praveen T N