2 comments

[ 2.8 ms ] story [ 14.8 ms ] thread
Note: This is Part 1 of 3 in our LLM Quantization series.

Part 1: What Even is an LLM? Part 2: Why do LLMs Need So Much VRAM? (coming soon) Part 3: How Do We Compress an LLM? (coming soon)

Makes me think somewhere out there exists a tiny micro SD card worth potentially billions of dollars.