NVIDIA Model Optimizer is a library that changes deep-learning models through techniques such as quantization, pruning, distillation, neural architecture search, speculative decoding, and sparsity so they can run more efficiently. Developers use it to optimize Hugging Face, PyTorch, or ONNX models and export checkpoints for inference frameworks such as SGLang, TensorRT-LLM, TensorRT, or vLLM. The catalogue entries provide skills, instructions, and a plugin for using its workflows.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add NVIDIA/Model-Optimizer --skill day0-releasegit clone --depth 1 https://github.com/NVIDIA/Model-OptimizerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nvidia/model-optimizer/day0-release)<a href="https://agentmods.dev/skills/nvidia/model-optimizer/day0-release"><img src="https://agentmods.dev/badge/skills/nvidia/model-optimizer/day0-release/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nvidia/model-optimizer/day0-release"><img src="https://agentmods.dev/badge/skills/nvidia/model-optimizer/day0-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00150 | $0.04394 |
| Opus 5.5 | $0.00060 | $0.01758 |
| Sonnet 5.5 | $0.00030 | $0.00879 |
| Haiku 4.5 | $0.00015 | $0.00439 |
Grade A, and why
day0-release scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 16d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Day-0 Release
Drive a model from a pretrained checkpoint to a publish decision for a quantized checkpoint, in a fixed sequence with a gate after every stage. This skill is a conductor: it sequences the existing domain skills and enforces the gates — it does not re-implement quantization, serving, evaluation, or comparison.
Goal (the default day-0 criterion): a quantized checkpoint smaller than the source, with accuracy drop within the threshold (default <1%) on the standard benchmark set versus the matching baseline, plus a publish recommendation.
When to use
Use only for the full goal-driven release. For a single stage, route to the domain skill directly: quantize → ptq, serve → deployment, evaluate → evaluation, compare two existing runs → compare-results.
Inputs
Resolve these before starting (ask the user for anything missing):
- Model — HF handle or checkpoint path.
- Recipe / qformat — e.g.
nvfp4,fp8, or a recipe path. One candidate for v1. - Cluster / launcher — from
clusters.yaml(see the common skill'senvironment-setup.md). - Eval set — defaults to the evaluation skill's AA suite
(
recipes/tasks/aa/). - Threshold — max accuracy drop; default
0.01(1%).
The chain
setup ─▶ PTQ ─▶ canary ─▶ baseline-eval ─▶ quantized-eval ─▶ compare ─▶ verbosity ─▶ closeout
│ │ │ │ │ │
gate_ptq /health gate_run gate_run gate_compare gate_verbosity
+ 1 gen
The evaluation skill deploys the model it evaluates (it stands up its own
endpoint per run), so there is no separate deploy stage — a serving failure
during evaluation surfaces through the eval gate (DEPLOYMENT_HEALTH_FAILED) and
triages to the deployment skill (see Step 4). The Step 2b canary is not
that: it runs before any evaluation precisely so an unservable checkpoint is
caught in ~15 min rather than after a multi-hour eval.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 16d ago Changed · +7 lines ddae30483ae0
- 1mo ago Changed · +2 lines bc49f84295a8
- 1mo ago First seen · 313 lines · 150 tokens per session scan A 596a7a649ee9
day0-release is a skill published in the GitHub repository NVIDIA/Model-Optimizer (5,398 stars, last pushed today), licensed Apache-2.0. It adds 150 tokens to every session and 4,394 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agentsop-llm-artifact-versioning
Enhancement overlay — version the WHOLE deployable LLM-app artifact as one bundle: prompts + compiled programs + model snapshot pins + retrieval config + eval-set version, versioned together so a deploy is reproducible and rollback is atomic. Activate when preparing to deploy an LLM app, when asking "what exactly is…
multi-repo-release
Prepares and validates GPT-RAG umbrella and multi-repository releases. Use whenever work involves release preparation, semantic versions, release branches, manifest or component pins, changelog release entries, tags, GitHub Release notes, or AI Landing Zone release alignment.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
release
Fully automate a release with version-bump and childhood.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.