gptq

github:zechenzhangAGI/claude-ai-research-skills · first committed 2025-11-09 · source · badge

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.

Skill Health: not yet scored

Listed, not yet scored. This skill has no public model test yet. It is in the scoring queue; submitted skills go first, then the most-installed.

Version history

5 commits to this file on GitHub (newest first).

2025-11-20 · commit 0a9ded4 · Standardize skill metadata: Add category tags and update authors
2025-11-20 · commit 51fc3a3 · Trigger upload of remaining 32 skills batch 2
2025-11-20 · commit 81c38fe · Upload all remaining 34 skills to Orchestra marketplace
2025-11-19 · commit bd4461f · Standardize YAML frontmatter for all 54 skills
2025-11-09 · commit 096b8f0 · feat: Add 8 comprehensive AI research skills (inference, optimization, tokenization, data)

Archived snapshots