Source: Quantization & Pruning: Make Models Small and Fast (Notebook tutorial)
The owner's tutorial on quantization (PTQ/QAT, INT8/INT4, GPTQ/AWQ/GGUF) and pruning.
Contents
- What: tutorial (owner’s Notebook site)
- Author: Loic (coolloic)
- Date: 2026
- Original: Quantization & Pruning: Make Models Small and Fast (Notebook tutorial)
Summary
An introductory tutorial contrasting quantization (fewer bits per weight) and pruning (fewer weights), with the affine quantization formula, PTQ vs QAT, dynamic vs static quantization, a survey of LLM methods and a PyTorch worked example.
Key claims
- Affine quantization: q = round(r/S) + Z and r ~ S(q - Z); symmetric uses Z = 0; per-channel scales beat per-tensor.
- Outliers stretch the range and coarsen the scale, which is why activations are harder to quantize than weights.
- PTQ needs no retraining (static PTQ needs a calibration pass); QAT simulates quantization in training and is more accurate at low bits.
- LLM inference is memory-bandwidth bound, so fewer bits per weight directly means more tokens per second.
- 8-bit is usually near-lossless, 4-bit often a good trade; below that quality degrades unevenly (reasoning, rare knowledge) beyond what perplexity shows.
- Lower precision only becomes faster if hardware and runtime support the format.