·gptq

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.

0Installs·0Trend·@ovachiever

Installation

$npx skills add https://github.com/ovachiever/droid-tings --skill gptq

SKILL.md

Post-training quantization method that compresses LLMs to 4-bit with minimal accuracy loss using group-wise quantization.

| Group Size | Model Size | Accuracy | Speed | Recommendation |

| -1 (per-column) | Smallest | Best | Slowest | Research only | | 32 | Smaller | Better | Slower | High accuracy needed | | 128 | Medium | Good | Fast | Recommended default | | 256 | Larger | Lower | Faster | Speed critical | | 1024 | Largest | Lowest | Fastest | Not recommended |

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning. Source: ovachiever/droid-tings.

View raw

Facts (cite-ready)

Stable fields and commands for AI/search citations.

Install command
npx skills add https://github.com/ovachiever/droid-tings --skill gptq
Category
</>Dev Tools
Verified
First Seen
2026-02-01
Updated
2026-02-18

Quick answers

What is gptq?

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning. Source: ovachiever/droid-tings.

How do I install gptq?

Open your terminal or command line tool (Terminal, iTerm, Windows Terminal, etc.) Copy and run this command: npx skills add https://github.com/ovachiever/droid-tings --skill gptq Once installed, the skill will be automatically configured in your AI coding environment and ready to use in Claude Code or Cursor

Where is the source repository?

https://github.com/ovachiever/droid-tings