Open Models Almanac
Methodsoptimizationquantization-aware training

methods · optimization

quantization-aware training

17 methods filed at this node or below it, from the sources of 13 models.

In this branch 17

Everything filed at this node or below it, with one collapsible heading per child node.

filed here 17

Quantization-Aware Training core · 10 sources · 10 quotes
MXFP4 Quantization default · 3 sources · 3 quotes
Stochastic Rounding used · 5 sources · 6 quotes
MXFP4 Quantization-Aware Training used · 4 sources · 4 quotes
MXFP4 Weights with MXFP8 Activations used · 2 sources · 3 quotes
12 single mentions
FP8 Quantization-Aware Training core · 1 source · 1 quote
Quantize-Dequantize Training core · 1 source · 1 quote
Calibration Data used · 1 source · 1 quote
FP4 Quantization used · 1 source · 1 quote
Freezing Non-Target Parameters used · 1 source · 1 quote
INT4 Quantization-Aware Training used · 1 source · 1 quote
NVFP4 Training used · 1 source · 1 quote
Per-Block Scalar Scaling used · 1 source · 1 quote
Q4_0 Quantization Format used · 1 source · 1 quote
Random Hadamard Transform used · 1 source · 1 quote
SFT-Based Quantization-Aware Distillation used · 1 source · 1 quote
Straight-Through Estimator used · 1 source · 1 quote

By model

Which of this branch's methods each model's own documents describe, and how strongly. Under each model: its strongest treatment anywhere in the branch.

↑