Honey, I shrunk the LLM! A beginner's guide to quantization – and testing it

Just be careful not to shave off too many bits ... These things are known to hallucinate as it is

Hands on  If you hop on Hugging Face and start browsing through large language models, you'll quickly notice a trend: Most have been trained at 16-bit floating point of Brain-float precision. …

source https://go.theregister.com/feed/www.theregister.com/2024/07/14/quantization_llm_feature/