quant-recipe-search

A guide for searching through multiple model-quantization recipes. Quantization reduces a model’s numerical precision to change its computing or memory requirements.

In plain words
What is it for?
Use it to design a quantization search, generate and validate candidate checkpoints, evaluate them, monitor jobs, and compare results.
Why use it?
It helps compare candidate recipes and decide which one best meets a chosen performance or resource goal instead of running a single unplanned attempt.

Skill for Claude CodeCodex

Part of the modelopt plugin — 18 skills shipped together

Install

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.

agentmods
npx agentmods add skills/nvidia/model-optimizer/quant-recipe-search
Any agent
npx skills add NVIDIA/Model-Optimizer --skill quant-recipe-search
Clone the repo
git clone --depth 1 https://github.com/NVIDIA/Model-Optimizer

Made for: Claude Code, Codex.

Or install modelopt, the plugin that ships this one along with the rest of its 18 skills.

Per session 148 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,915 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00148 $0.01915
Opus 5 $0.00074 $0.00958
Sonnet 5 $0.00030 $0.00383
Haiku 4.5 $0.00015 $0.00192

Measured 3d ago against content hash b7ea8395ff0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quant-recipe-search 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 3d 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.

plugins/modelopt/skills/quant-recipe-search/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use this skill when quantization is an iterative recipe search, not a one-off PTQ run. The skill owns strategy: define success, choose the search space, sequence candidates, and decide the next iteration. It delegates checkpoint generation, serving, evaluation, monitoring, and metric comparison to the existing execution skills.

Treat a direct request such as "find the best quantization recipe and generate a PTQ checkpoint for this model" as enough to start. Recover local state first, then ask only for missing decisions that change the search.

Skill Boundaries

  • Use ptq to produce and validate checkpoints.
  • Use deployment to serve checkpoints and debug serving-specific flags.
  • Use evaluation to create NEL configs and submit evals.
  • Use launching-evals to run, resume, debug, and analyze NEL runs.
  • Use monitor for active job tracking.
  • Use accessing-mlflow for MLflow artifact lookup.
  • Use compare-results for validated baseline-vs-candidate deltas and score-field comparability.

Do not duplicate those workflows here. This skill should leave the user with a clear recipe portfolio, success metric, experiment sequence, and next decision.

Problem

The task is to find the best recipe for a user-defined target, not merely to produce a quantized checkpoint. A generated PTQ checkpoint is only a candidate. It becomes a recommended recipe only after evaluation and comparison against the matching baseline.

Required inputs before planning candidates:

  • Optimization goal: compute/throughput, memory/latency, or a custom metric.
  • Primary quantization family: for example NVFP4, W4A16 NVFP4, FP8/W8A8, INT4/AWQ, or a custom mixed set.
  • Benchmark set or baseline results: the user-defined acceptance surface.

If any of these are missing, ask for them. Do not silently default to FP8/W8A8 or call a checkpoint "best" before evaluation.

Default success rule: maximize the chosen performance objective while keeping each benchmark within 1 percentage point of the matching BF16/FP16 baseline. Near-threshold or noisy regressions require reruns before making a decision.

Read the full file on GitHub · 168 lines

Files

What ships with it

2 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.

Changes

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.

  1. 3d ago First seen · 168 lines · 148 tokens per session scan A b7ea8395ff0c

Subscribe to this mod's changes

quant-recipe-search is a skill published in the GitHub repository NVIDIA/Model-Optimizer (3,675 stars, last pushed yesterday), licensed Apache-2.0. It adds 148 tokens to every session and 1,915 once invoked, about $0.0007 per session on Opus 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.

Related

Other skills, from other repositories

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

bigquery-ai-ml

Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity…

google/skills · 104 tokens

ondb

A logical analysis and reasoning tool for AI. Use when decomposing documents into structured knowledge, querying entities and relations, validating consistency, or indexing files. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", "analyze this document", entity CRUD, or cross-skill…

x-cmd/x-cmd · 71 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

mixed-precision

Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.

aiming-lab/AutoResearchClaw · 25 tokens

sparse-autoencoder-training

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

Orchestra-Research/AI-Research-SKILLs · 58 tokens