Individual skill
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.
10-optimization/gptq/SKILL.md
Source commit 773a52944ba4747a18bd4ae9ade53fff041adcbc
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 9, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 14,493
- Repository last updated
- Oct 11, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ai Repository topic
- ai-research Repository topic
- claude Repository topic
- claude-code Repository topic
- claude-skills Repository topic
- codex Repository topic
- gemini Repository topic
- gpt-5 Repository topic
- grpo Repository topic
- huggingface Repository topic
- optimization Declared skill tag
- gptq Declared skill tag
- quantization Declared skill tag
- 4-bit Declared skill tag
- post-training Declared skill tag
- memory-optimization Declared skill tag
- consumer-gpus Declared skill tag
- fast-inference Declared skill tag
- qlora Declared skill tag
- group-wise-quantization Declared skill tag
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 11,593 bytesSKILL.mdcore · 11,593 bytesSKILL.mdcore · 11,593 bytesSKILL.mdcore · 11,593 bytesSKILL.mdcore · 11,593 bytesSKILL.mdcore · 11,593 bytesSKILL.mdcore · 11,593 bytesSKILL.mdcore · 11,593 bytesSKILL.mdcore · 11,593 bytesSKILL.mdcore · 11,593 bytesSKILL.mdcore · 11,593 bytesSKILL.mdcore · 11,593 bytesSKILL.mdcore · 11,593 bytesSKILL.mdcore · 11,593 bytesSKILL.mdcore · 11,593 bytesSKILL.mdcore · 11,593 bytesSKILL.mdcore · 11,593 bytesreferences/calibration.mddoc · 8,164 bytesreferences/integration.mddoc · 2,797 bytesreferences/troubleshooting.mddoc · 1,899 bytes
Read excerpt
# GPTQ (Generative Pre-trained Transformer Quantization)
Post-training quantization method that compresses LLMs to 4-bit with minimal accuracy loss using group-wise quantization.
## When to use GPTQ
**Use GPTQ when:**
- Need to fit large models (70B+) on limited GPU memory
- Want 4× memory reduction with <2% accuracy loss
- Deploying on consumer GPUs (RTX 4090, 3090)
- Need faster inference (3-4× speedup vs FP16)
**Use AWQ instead when:**
- Need slightly better accuracy (<1% loss)