Module 4 — Modern LLM Concepts·Lesson 18 of 22

4.5 Quantization & Efficiency

Interview-ready field notes

The 20-second answer

Quantization stores or computes model values with fewer bits, cutting memory and often speeding inference while accepting some numerical error.

Core ideas to retain

  • FP32, BF16/FP16, INT8, and 4-bit formats trade precision for memory. Weight memory is roughly parameters ×\times bytes per value.
  • Post-training quantization converts an existing model; quantization-aware training simulates quantization while training and can preserve accuracy better.
  • Per-channel or group-wise scales usually preserve quality better than one global scale because tensor ranges differ.
  • Quantizing weights reduces model memory; long-context generation can still be dominated by KV-cache memory and bandwidth.

Interview / OA rule

Say what is quantized: weights, activations, KV cache, or all three. Memory savings do not automatically mean proportional speedup; hardware and bandwidth matter.

One good written resource

Hugging Face — Quantization — read this after the video when you want a clearer mental model, not more pages of notes.

Most asked

Interview questions to practise aloud

Each answer is the level of detail expected for a strong fundamentals round.

01

Why quantize an LLM?

To fit it in less memory and often improve throughput or latency. The cost is approximation error and possible hardware/kernel constraints.

02

INT8 vs 4-bit?

Four-bit saves more memory but introduces more error and may require better quantization schemes. INT8 is generally a safer quality–efficiency compromise.

03

What is QLoRA?

It stores a frozen base model in low-bit form and trains LoRA adapters, enabling fine-tuning with much lower memory than full precision full fine-tuning.