Fig. 5From: RUBICON: a framework for designing efficient deep learning-based genomic basecallersComparison of average basecalling throughput for RUBICALL-MP with state-of-the-art basecallers in terms of a average basecalling accuracy, b model parameters, and c model size. RUBICALL-MP provides higher compute performance with lower model size when compared to RUBICALL-FP because of the mixed-precision computationBack to article page