howtospark
Training

MXFP4 quantization

FP4 microscalingReference

OCP microscaling FP4, block size 32 — the open cross-vendor standard.

Relieves
CapacityBandwidthCompute
Targets
Weights · Activations
Format
MXFP4 (E2M1, block 32)
Granularity
Microscaling — block size 32
Lifecycle
PTQ · no gradients
Calibration
Small calibration set
Compression
~4× vs BF16
Quality
Good; block 32 adapts less locally than NVFP4
Hardware
Blackwell / MX-capable tensor cores for speedup
Runtimes
vLLMTensorRT-LLM

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