model,engine,npl,decode_agg_tps,decode_perseq_tps,prefill_tps,ttft_mean_ms,peak_gb
q36-27b-nvfp4,llama,8,82.5,9.57,507.3,6038.1,53.51
q36-27b-nvfp4,llama,32,192.6,4.79,115.0,133551.7,69.63
q36-27b-nvfp4,llama,64,277.8,3.09,95.9,321618.8,83.96
q36-27b-nvfp4,llama,128,384.6,1.86,69.7,902762.7,93.82
q36-27b-nvfp4,vllm,8,70.4,8.76,2096.2,1861.1,110.92
q36-27b-nvfp4,vllm,32,211.8,6.28,2182.6,5353.2,110.87
q36-27b-nvfp4,vllm,64,309.1,4.38,2088.9,9512.4,110.88
q36-27b-nvfp4,vllm,128,418.8,2.79,1929.1,18449.5,110.95
q36-35b-a3b-nvfp4,llama,8,211.8,24.45,1236.4,2477.1,39.66
q36-35b-a3b-nvfp4,llama,32,393.0,10.02,1213.9,8225.2,47.11
q36-35b-a3b-nvfp4,llama,64,527.0,6.15,1152.3,15849.5,57.13
q36-35b-a3b-nvfp4,llama,128,726.4,3.73,276.8,213017.2,61.51
q36-35b-a3b-nvfp4,vllm,8,256.5,31.84,5186.5,768.8,109.62
q36-35b-a3b-nvfp4,vllm,32,500.8,14.90,6223.4,1830.4,109.63
q36-35b-a3b-nvfp4,vllm,64,686.1,9.83,5926.5,3224.4,109.63
q36-35b-a3b-nvfp4,vllm,128,882.2,6.05,5300.5,6487.7,109.64