← All skills
ptq
80 / 100 · Low risk
Fine to try.
By NVIDIA/Model-Optimizer (GitHub) · other · 5,579 stars · scanned at commit 6713c5a
Use when the user asks to "quantize a model", "run PTQ", "post-training quantization", "NVFP4 quantization", "FP8 quantization", "INT8 quantization", "INT4 AWQ", "quantize LLM", "quantize MoE", "quantize VLM", or needs to produce a quantized HuggingFace checkpoint from a pretrained model using ModelOpt. Do NOT use for multi-candidate recipe exploration or optimization (use quant-recipe-search).
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
The author does not mention this. It runs automatically when the plugin is installed.
Found in 9 places.
Show 6 more
Downloads and installs other software
The author does not mention this. It runs automatically when the plugin is installed.
Found in 14 places.
Show 11 more
- plugins/modelopt/skills/ptq/SKILL.md, line 194
- **Linear-attention models** (Qwen3-Next/3.5/3.8, GLM-5.x Flash, Kimi Linear, OLMo Hybrid) fall back to slow, memory-hungry PyTorch kernels without `pip instal - plugins/modelopt/skills/ptq/references/slurm-setup-ptq.md, line 34
pip install -U transformers - plugins/modelopt/skills/ptq/references/slurm-setup-ptq.md, line 39
**Prefer `pip install -e ".[hf]" --no-build-isolation`** (run from the Model-Optimizer repo root) to make the synced ModelOpt source importable in the container - plugins/modelopt/skills/ptq/references/slurm-setup-ptq.md, line 42
pip install -e ".[hf]" --no-build-isolation - plugins/modelopt/skills/ptq/references/slurm-setup-ptq.md, line 55
pip install -U transformers # now upgrades and resolves with new deps included - plugins/modelopt/skills/ptq/references/slurm-setup-ptq.md, line 61
pip install -U transformers --no-deps - plugins/modelopt/skills/ptq/references/unsupported-models.md, line 20
First, if README or `config.json` specifies a required transformers version, check if installed version satisfies it. If not, upgrade: `pip install -U "transfor - plugins/modelopt/skills/ptq/references/unsupported-models.md, line 47
- **Raises `ValueError` / `OSError` (unknown architecture)** → not in the installed transformers. Try `pip install -U transformers` first. If still not found, c - plugins/modelopt/skills/ptq/references/unsupported-models.md, line 54
- **Found** → `pip install /tmp/transformers-main`, then re-run `AutoConfig`. - plugins/modelopt/.claude-plugin/plugin.json, line 22
"command": "uvx", - plugins/modelopt/.mcp.json, line 3
"command": "uvx",
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'ptq' ] || [ -L ~/.agents/skills/'ptq' ]; then echo 'A skill folder named ptq already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/NVIDIA/Model-Optimizer' "$d" && git -C "$d" checkout --quiet '6713c5a679fab80fdd9b688df01845f545c307b1' -- 'plugins/modelopt/skills/ptq' && mkdir -p ~/.agents/skills && cp -R "$d"/'plugins/modelopt/skills/ptq' ~/.agents/skills/'ptq' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'ptq' ~/.claude/skills/'ptq' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for NVIDIA/Model-Optimizer shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/NVIDIA/Model-Optimizer/)
Score history
| Date | Version | Score |
|---|
| 2026-11-10 | 6713c5a | 80 |