Skip to content
inference.academy

glossary/precision/fp4

FP4

also NVFP4, MXFP4, E2M1

A 4-bit float with sixteen representable values, usable only with fine-grained scaling: a shared scale factor per small block of values restores the range the format lacks. Blackwell runs it on tensor cores at twice the FP8 rate. It quarters the weight bytes of BF16, which for a memory-bound decode is a fourfold cut in the floor per token, at a quality cost that depends heavily on the model and the calibration.


35 GB

For Llama 3 70B's weights at half a byte each; the KV cache, if left in BF16, then dominates memory at long context.


See it happen


Related