Tag
#quantization
2posts
AI & Agents6 min read
FP4: the 16-value float powering billion-parameter models
FP4, a 4-bit float with just 16 representable numbers, is now the default inference format for billion-parameter models on NVIDIA Blackwell hardware.
#machine-learning#floating-point#nvidia
AI & Agents3 min read
BitNet: The Era of 1-bit LLMs is Finally Here
Explore bitnet.cpp, Microsoft's official framework for 1-bit LLMs that replaces multiplications with additions for massive speedups.
#ai#llm#quantization