#! /bin/bash

export CUDA_VISIBLE_DEVICES="6,7"

MODEL="/home/kongcunliang/workspace/pretrained-models/unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF/UD-Q4_K_XL/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_XL-00001-of-00003.gguf"

llama-server \
  --model $MODEL \
  --alias "nemotron-3-super" \
  --temp 0.6 \
  --top-p 0.95 \
  --ctx-size 262144 \
  --host 0.0.0.0 \
  --port 8001 \