Encyclopedia · 176 concepts

Architectures · advanced · concept 67 of 176

Model Quantization & Compression

Reducing model size and computational cost by using lower-precision numbers (e.g., 32-bit → 4-bit floats). Enables running LLMs on consumer hardware. GPTQ, GGUF, and AWQ are popular methods.

Key terms

INT8INT4GPTQGGUFAWQMixed precision

Learn these first

Where you meet it in the real world

Running LLMs locally, mobile AI, edge deployment

Guides and articles

Courses, papers, and more