Share your thoughts, 1 month free Claude Pro on usSee more

Home/Benchmarks

Efficiency Evaluation on GPT-2 124M

1Inference Speed (x)

FP32 Baseline

Updated 1mo ago

Evaluation Results

Method	Links
FP32 Baseline 2026.01		1	-

SOTA Paper

FP32 Baseline

Power-of-Two Quantization-Aware-Training (PoT-QAT) in Large Language Models (LLMs)

Dataset

GPT-2

Follow for update

@wizwand_team Discord

Related Benchmarks

Language Modeling on OpenWebText GPT-2 124M (val)

© 2026 wizwand

Blog Contact Changelog Swarm

Privacy Policy Terms of Service FAQs Swarm Docs