GPTQ — post-training 4-bit quantization for LLMs with minimal accuracy loss
Compress LLMs to 4-bit with group-wise quantization — 4× memory reduction, <2% perplexity loss, 3-4× faster inference; AutoGPTQ guides, kernel backends (ExLlamaV2, Marlin, Triton), transformers integration, QLoRA fine-tuning
- What
- Compress LLMs to 4-bit with group-wise quantization — 4× memory reduction, <2% perplexity loss, 3-4× faster inference; AutoGPTQ guides, kernel backends (ExLlamaV2, Marlin, Triton), transformers integration, QLoRA fine-tuning
- Cost
- Free
- Needs
- an NVIDIA CUDA GPU and Python — the skill is a quantization workflow guide, not the software itself
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @davila7's gptq skill: a practical guide to GPTQ post-training quantization for running large LLMs on limited GPU memory. Covers when to use GPTQ vs AWQ vs bitsandbytes, quick start (install AutoGPTQ, load pre-quantized models from HuggingFace, quantize your own model with calibration data), group-wise quantization mechanics and the group-size trade-off table, three configs (standard 4-bit recommended, 3-bit high-compression, 4-bit maximum accuracy), kernel backends (ExLlamaV2 default-fastest, Marlin for Ampere+, Triton Linux-only), direct transformers integration, QLoRA fine-tuning (a 70B model trainable on a single A100 80GB), performance benchmarks (memory reduction per model, tokens/sec, WikiText-2 perplexity degradation <2%), common patterns (multi-GPU, CPU offloading, batch inference), and how to find pre-quantized models. Honest caveats: targets CUDA GPUs (RTX 4090, A100 class) — limited CPU/Mac utility; AutoGPTQ and backend versions move fast; model quality claims reflect the benchmarks quoted, verify on your workload. MIT licensed (frontmatter and manifest agree). Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
GPTQ is a free Muse skill, a practical guide to GPTQ post-training quantization for running large LLMs on limited GPU memory. It covers when to use GPTQ versus AWQ versus bitsandbytes, quick start with AutoGPTQ, group-wise quantization mechanics and the group-size trade-off table, three configs, kernel backends including ExLlamaV2, Marlin and Triton, direct transformers integration, and QLoRA fine-tuning.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 18, 2026📌 Pinned version: commit 46b4d8bStep 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: an NVIDIA CUDA GPU and Python — the skill is a quantization workflow guide, not the software itself Install "GPTQ — post-training 4-bit quantization for LLMs with minimal accuracy loss" for me. It gives my agent @davila7's GPTQ workflow: choose between GPTQ/AWQ/bitsandbytes, install AutoGPTQ, load pre-quantized models or quantize my own with calibration data, pick a quantization config (standard 4-bit, 3-bit high-compression, or 4-bit max accuracy) and kernel backend (ExLlamaV2, Marlin, Triton), integrate with transformers, run QLoRA fine-tuning, and apply the memory/inference benchmarks and deployment patterns (multi-GPU, CPU offloading, batch inference). MIT-licensed. Repository: https://raw.githubusercontent.com/davila7/claude-code-templates/46b4d8b1c051e9fd0f8fdd739b15f7f5e8942608/cli-tool/components/skills/ai-research/optimization-gptq/SKILL.md Pinned version: install the code at commit 46b4d8b1c051e9fd0f8fdd739b15f7f5e8942608 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "gptq". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. install auto-gptq/transformers myself and pick my target model; nothing else — it's a methodology). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 46b4d8b · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 18, 2026 · Observed during the install test: registry.npmjs.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.