Quantization
Storing model weights in fewer bits, such as FP8 or INT8, to shrink memory and speed up inference. Modern methods lose little quality on most tasks.
What is Quantization?
Storing model weights in fewer bits, such as FP8 or INT8, to shrink memory and speed up inference. Modern methods lose little quality on most tasks.
Quantization is a advanced concept that sits in the LLM and GenAI Ops area of system design. Engineers reach for it whenever they need to reason about real-world trade-offs in that space, not just for textbook correctness, but because real production systems at companies like Netflix, Amazon, and Google make these decisions every day.
If you want to go deeper than this definition, with diagrams, code, and a quiz to lock it in, work through the "LLM Inference Optimization" lesson linked below. It walks through the why, the mechanism, the trade-offs, and how the giants actually use it in production.
Learn Quantization in depth
Full interactive lesson with diagrams, code examples, real-world references, and a quiz.
Open the LLM Inference Optimization lessonRelated lessons
Lessons that touch on Quantization as part of a larger topic.
Embedding Storage
How to efficiently store, manage, and serve high-dimensional embedding vectors at scale
intermediate · database types storage
Scaling and GPU Infrastructure: Serving Models Without Burning Money
Why GPU serving gets expensive and how to fix it: batching, quantization, distillation, caching, autoscaling, cold starts, and horizontal vs vertical scaling
ml-foundation · core
See also
Related glossary terms you might want to look up next.
KV Cache
The stored keys and values of every token processed so far, kept so attention does not recompute the whole history each step. It grows with every token and is what limits how many conversations a GPU can serve.
Inference Optimization
The engineering that serves more tokens per GPU-second: KV caching, continuous batching, quantization, prefix caching, and speculative decoding. Serving cost is dominated by how well these are done.
LoRA (Low-Rank Adaptation)
A parameter-efficient fine-tuning method that freezes the base weights and trains a small pair of low-rank matrices instead, cutting memory and cost while keeping most of the quality.
RAG (Retrieval-Augmented Generation)
A pattern that retrieves relevant text from an external index and puts it in the model's prompt so the answer is grounded in current, verifiable facts rather than the model's memory.
Embedding
A list of numbers that represents the meaning of a piece of text, so that similar meanings sit close together in vector space. The same model must embed both the corpus and the query.
ANN (Approximate Nearest Neighbor)
Search that finds vectors close to a query without scanning every item, trading a small chance of missing a true neighbor for a large gain in speed. HNSW and IVF are the common indexes.