Show HN: Quant Picker – which GGUF file fits your model and machine
Category: devtools
Tags: llm, quantization, gguf
Score: 5.3/10 (Innovation: 5, Technical: 5, Documentation: 6, Utility: 6)
Quant Picker is a web tool that calculates which quantization level (GGUF file) best fits a given model and machine by considering file size, memory, and desired context length. It automates the community's quantization recommendation logic, making it easier for users to select the optimal quant for their hardware.
Target audience: backend devs, data engineers
Repository: https://vettedconsumer.com/quant-picker/
View on Hacker News