model_name: "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8"
accuracy_threshold: 0.93
num_questions: 1319
num_fewshot: 5
startup_max_wait_seconds: 1200
server_args: >-
  --enforce-eager
  --max-model-len 4096
  --tensor-parallel-size 8
  --enable-expert-parallel
  --speculative-config '{"method":"mtp","num_speculative_tokens":5}'