skillrank_skill ▸ google-ai-edge/accuracy-safe-quantizationMIT · open registry

skill detail

← registry

Accuracy Safe Quantization

google-ai-edge/accuracy-safe-quantization

Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe for a new model, when a quantized model fails to load, degrades on a task...

communityprovisionalaishrinkconvertedlitert

skillrank score

█████░░░░░░░░░░░34

SkillRank score blends community stars, real usage, and our eval lift; provisional until a skill is evaluated -- so popularity alone can't reach the top tier.

source

★ 392

google-ai-edge/litert-samples

skills/accuracy-safe-quantization

open on GitHub ▸

eval status

eval pending

Success delta, token delta, and trial count are not available yet. No eval number is shown until this skill has measured results.

install

$ skillrank install google-ai-edge/accuracy-safe-quantization
$ curl -fsSL skillrank.dev | sh