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

Large Language Model Inference on Chatbot Instruction Prompts and Finance Alpaca (test)

265.7Throughput (TPS)

Aurora (Qwen3-Coder-Next (FP8))

45.012102.306159.6216.894Feb 6, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
265.7264.8208.7320.51.513.06
2026.02
211.8210.6163.1270.31.572.62
2026.02
176.4178172.3178.4--
2026.02
146.3143.5109.6189.51.233.07
2026.02
134.9136.4130.6136.9--
2026.02
119.8121.5104.8134.6--
2026.02
107.6103.775.7156.61.093.06
2026.02
107.1104.579.9137.11.362.62
2026.02
99.6102.174.5119.2--
2026.02
83.182.960.91121.292.62
2026.02
7978.773.785.1--
2026.02
67.164.744100.51.252.62
2026.02
64.563.758.972.3--
2026.02
53.552.947.167.1--