Inference Quantize Calibrate

Produce quantized inference weights from a BF16/FP8 base checkpoint via a post-training-quantization (PTQ) pipeline -- instead of only ever pulling NVFP4 weights pre-quantized. A calibration prep Job then a quantize Job: NVIDIA ModelOpt -> NVFP4 (default), or llm-compressor -> FP8 (alt). Writes weights + per-layer scales to an experiment-prefixed PVC, gated on inference-model-eval accuracy + a perf A/B. When a vendor nvidia/*-NVFP4 exists, runs a 3-way comparison (base vs ours vs NVIDIA) on accuracy + perf + ncu. Ack-gated. The calibrate+quantize phase of inference-model-optimize. Triggers on "quantize a model", "calibrate NVFP4", "run modelopt PTQ", "produce NVFP4 weights", "llm-compressor FP8", "PTQ pipeline", "compare our PTQ to NVIDIA NVFP4", "our nvfp4 vs nvidia nvfp4", "calibration dataset for quantization", "quantize <model> to NVFP4/FP8", or any combination of "quantize / calibrate / PTQ / modelopt / llm-compressor" with "nvfp4 / fp8 / weights / model / inference".

mkdir -p ~/.claude/skills/inference-quantize-calibrate
curl -L https://claudskills.com/skills/inference-quantize-calibrate/SKILL.md \
  -o ~/.claude/skills/inference-quantize-calibrate/SKILL.md

@misc{inference-quantize-calibrate-2026,
  author    = {cfregly},
  title     = {Inference Quantize Calibrate [Claude Code skill]},
  year      = {2026},
  publisher = {ClaudSkills},
  url       = {https://claudskills.com/skills/inference-quantize-calibrate/}
}