General  ·  Wild GitHub

gptq

Post-training 4-bit quantization for LLMs with minimal accuracy loss.


Composite

4.4

C 4.4 · A 0.0

How we got there

Craft · D1–D5

D1 · Trigger clarity 4.5
D2 · Output specificity 4.5
D3 · Scope precision 4.5
D4 · Self-containment 4.5
D5 · Reusability 4.0

02 — Cross-validation

1 source verified

Install

Use this skill

/plugin install gptq

Auto-indexed. Editorial review pending — score is based on the rubric only.