howtospark
Training

bitsandbytes NF4 / LLM.int8

QuantizationReference

Zero-calibration load-time quant; NF4 is the base for QLoRA fine-tuning.

Relieves
Capacity
Targets
Weights
Format
NF4 / INT8
Granularity
Per-block (NF4 block 64)
Lifecycle
PTQ · no gradients
Calibration
No calibration
Compression
2–4×
Quality
Good; NF4 fitted to a normal weight distribution
Hardware
CUDA; bitsandbytes kernels
Runtimes
Transformers

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