Benchmark Radar™
Star —

DistilBERT ONNX Quantization Benchmark

Explore score history ↗

An end-to-end ONNX quantization benchmark for a DistilBERT sentiment classifier, comparing PyTorch FP32, ONNX FP32, dynamic INT8, and static INT8 variants on accuracy, latency, and model size using a fixed 200-sample SST-2 validation set.

Released
2026-09-06
Evaluates
General AI, Language & Knowledge, cs.AI
Openness
unknown
Importer
Claire Radar
Review status
source-reviewed-exclude

DistilBERT ONNX Quantization Benchmark code

No reported scores are on record for this benchmark yet.

Which sources cite DistilBERT ONNX Quantization Benchmark?

Related General AI, Language & Knowledge, cs.AI benchmarks