Agent Skill
Gptq skill
gptqOrchestra-Research/AI-Research-SKILLs10-optimization/gptq/SKILL.md
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.
always on
84 tokname + description
once used
3,298 tokSKILL.md body
bundled files
313 KB
repo stars
14kGitHub
Install the Gptq skill
Skills CLI (Claude Code, Codex, Cursor and others)
npx skills add https://github.com/Orchestra-Research/AI-Research-SKILLs --skill gptq
Claude Code, by hand (all projects)
git clone --depth 1 https://github.com/Orchestra-Research/AI-Research-SKILLs.git /tmp/AI-Research-SKILLs mkdir -p ~/.claude/skills cp -R /tmp/AI-Research-SKILLs/10-optimization/gptq ~/.claude/skills/gptq
For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.
What it costs your context
Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.
| When | What loads | Cost |
|---|---|---|
| Every session | Name and description | 84 tok |
| When the agent uses it | The SKILL.md instructions | 3,298 tok |
| Only if opened | 3 bundled files (13 KB) | varies |
Until it is used, gptq costs about 16× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 98 skills from Orchestra-Research/AI-Research-SKILLs would load 6,174 tokens of descriptions. Skills vs MCP study
Checks
Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.
Checked 2026-10-22 · method
What's inside
The headings of its SKILL.md. Read the full file on GitHub.
- GPTQ (Generative Pre-trained Transformer Quantization)
- When to use GPTQ
- Quick start
- Installation
- Load pre-quantized model
- Quantize your own model
- Group-wise quantization
- Quantization configurations
- Standard 4-bit (recommended)
- High accuracy (3-bit with larger groups)
- Maximum accuracy (4-bit with small groups)
- Kernel backends
- ExLlamaV2 (default, fastest)
- Marlin (Ampere+ GPUs)
- Triton (Linux only)
- Integration with transformers
- Direct transformers usage
- QLoRA fine-tuning (GPTQ + LoRA)
- Performance benchmarks
- Memory reduction
- Inference speed (Llama 2-7B, A100)
- Accuracy (perplexity on WikiText-2)
- Common patterns
- Multi-GPU deployment
More skills from Orchestra-Research/AI-Research-SKILLs
- academic-plottingOrchestra-Research/AI-Research-SKILLs
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn. Use when creating any figure for a conference paper.
14k67 tok idle · 5,308 in use - ara-compilerOrchestra-Research/AI-Research-SKILLs
Compiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a complete Agent-Native Research Artifact (ARA) with cognitive layer (claims, concepts, heuristics), physical layer (configs, code stubs), exploration graph, and grounded evidence. Use when ingesting a paper or codebase into a structured, machine-executable knowledge package, building an ARA from scratch, or converting research outputs into a falsifiable, agent-traversable form.
14k106 tok idle · 3,117 in use - ara-research-managerOrchestra-Research/AI-Research-SKILLs
Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during execution — to maintain a faithful, auditable trace of how a research project actually evolved.
14k91 tok idle · 2,841 in use - ara-rigor-reviewerOrchestra-Research/AI-Research-SKILLs
Performs ARA Seal Level 2 semantic epistemic review on Agent-Native Research Artifacts, scoring six dimensions (evidence relevance, falsifiability, scope calibration, argument coherence, exploration integrity, methodological rigor) and producing a constructive, severity-ranked report with a Strong Accept-to-Reject recommendation. Use after Level 1 structural validation passes, when an ARA needs an objective epistemic critique before publication or release.
14k90 tok idle · 4,013 in use - audiocraft-audio-generationOrchestra-Research/AI-Research-SKILLs
PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.
14k54 tok idle · 3,633 in use - autogpt-agentsOrchestra-Research/AI-Research-SKILLs
Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.
14k38 tok idle · 2,137 in use - autoresearchOrchestra-Research/AI-Research-SKILLs
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.
14k98 tok idle · 5,151 in use - awq-quantizationOrchestra-Research/AI-Research-SKILLs
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.
14k79 tok idle · 2,318 in use