Sitemap
Every page on Quantization.com.
Site
- About
- Advertise and sponsor
- Careers and talent
- Cheat sheet
- Contact
- Cookie policy
- Disclaimer
- Formats atlas
- Free optimization plan
- Privacy policy
- Quantization Challenge
- Quantization glossary
- Quantization.com — LLM Quantization Tools, VRAM Calculator & Guides
- Resources
- Sitemap
- Support the project
- Terms of use
- Trademark and copyright
- Videos
Tools
Learn
- ADC quantization error, SQNR and ENOB explained
- Audio bit depth and dither: 16-bit, 24-bit, 32-bit float
- Choosing hardware for local LLMs: memory first, bandwidth second
- GGUF quant types explained: legacy, k-quants and i-quants
- GPTQ vs AWQ vs GGUF vs EXL2: LLM quantization methods compared
- How to quantize a model yourself, step by step
- KV cache quantization: the memory math and how to do it
- LLM quantization: the complete practical guide
- Learn: all guides
- Number formats for AI: from FP32 to FP8, NF4, MXFP4 and ternary
- PTQ vs QAT: post-training quantization and quantization-aware training
- Quantization in physics: why energy comes in steps
- Quantize in music production: grid, strength, swing and groove
- What is quantization? One idea behind AI, audio, music and physics