howtospark
Training

SqueezeLLM

Reduce model sizeQuantizationReference

Non-uniform quantization that places quant levels by second-order sensitivity, with rare outliers kept sparse in FP16 — more bits, effectively, where they matter.

Objective
Reduce model size · Lossy
Relieves
CapacityBandwidth
Targets
Weights
Format
3-bit non-uniform LUT + dense-and-sparse split
Granularity
Sensitivity-weighted, per-channel codebooks
Lifecycle
PTQ · no gradients
Calibration
Small calibration set
Compression
~5× (3-bit)
Quality
Strong at 3-bit; sensitivity weighting beats uniform 3-bit
Hardware
LUT dequant + sparse-matrix kernels
Runtimes

A worked Spark recipe for this method hasn't been written yet — it lives here as a reference point in the ontology.