diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml
index 33751270b..56d95539e 100644
--- a/.github/configs/nvidia-master.yaml
+++ b/.github/configs/nvidia-master.yaml
@@ -1789,6 +1789,24 @@ qwen3.5-fp8-b200-sglang:
     - { tp: 8, ep: 1, conc-start: 4, conc-end: 16 }
     - { tp: 4, ep: 4, conc-start: 16, conc-end: 128 }
 
+qwen3.5-fp4-b200-sglang:
+  image: lmsysorg/sglang:v0.5.9-cu129-amd64
+  model: nvidia/Qwen3.5-397B-A17B-NVFP4
+  model-prefix: qwen3.5
+  runner: b200
+  precision: fp4
+  framework: sglang
+  multinode: false
+  seq-len-configs:
+  - isl: 1024
+    osl: 1024
+    search-space:
+    - { tp: 4, ep: 1, conc-start: 4, conc-end: 128 }
+  - isl: 8192
+    osl: 1024
+    search-space:
+    - { tp: 4, ep: 1, conc-start: 4, conc-end: 128 }
+
 glm5-fp8-b200-sglang:
   image: lmsysorg/sglang:nightly-dev-cu13-20260317-1eea7448
   model: zai-org/GLM-5-FP8
diff --git a/benchmarks/single_node/qwen3.5_fp4_b200.sh b/benchmarks/single_node/qwen3.5_fp4_b200.sh
new file mode 100755
index 000000000..c26421059
--- /dev/null
+++ b/benchmarks/single_node/qwen3.5_fp4_b200.sh
@@ -0,0 +1,101 @@
+#!/usr/bin/env bash
+
+source "$(dirname "$0")/../benchmark_lib.sh"
+
+check_env_vars \
+    MODEL \
+    TP \
+    CONC \
+    ISL \
+    OSL \
+    RANDOM_RANGE_RATIO \
+    RESULT_FILENAME \
+    EP_SIZE
+
+if [[ -n "$SLURM_JOB_ID" ]]; then
+  echo "JOB $SLURM_JOB_ID running on $SLURMD_NODENAME"
+fi
+
+nvidia-smi
+
+hf download "$MODEL"
+
+export NCCL_NVLS_ENABLE=1
+export SGL_ENABLE_JIT_DEEPGEMM=false
+export SGLANG_ENABLE_FLASHINFER_GEMM=true
+export PYTHONUNBUFFERED=1
+
+SERVER_LOG=/workspace/server.log
+PORT=${PORT:-8888}
+
+# Default: recv every ~10 requests; if CONC >= 16, relax to ~30 requests between scheduler recv polls.
+if [[ $CONC -ge 16 ]]; then
+  SCHEDULER_RECV_INTERVAL=30
+else
+  SCHEDULER_RECV_INTERVAL=10
+fi
+
+MEM_FRAC_STATIC=0.85
+CHUNKED_PREFILL_SIZE=32768
+MAX_PREFILL_TOKENS=32768
+CUDA_GRAPH_MAX_BATCH_SIZE=$CONC
+MAX_RUNNING_REQUESTS=128
+CONTEXT_LENGTH=$((ISL + OSL + 20))
+if [ "${EVAL_ONLY}" = "true" ]; then
+    setup_eval_context
+    CONTEXT_LENGTH="$EVAL_MAX_MODEL_LEN"
+fi
+
+if [[ $TP -eq 8 ]]; then
+  EXTRA_ARGS="--enable-flashinfer-allreduce-fusion"
+else
+  EXTRA_ARGS=""
+fi
+
+echo "SCHEDULER_RECV_INTERVAL: $SCHEDULER_RECV_INTERVAL, CONC: $CONC, ISL: $ISL, OSL: $OSL"
+
+# Start GPU monitoring (power, temperature, clocks every second)
+start_gpu_monitor
+
+set -x
+PYTHONNOUSERSITE=1 python3 -m sglang.launch_server --model-path=$MODEL --host=0.0.0.0 --port=$PORT \
+--trust-remote-code \
+--tensor-parallel-size=$TP --data-parallel-size=1 --ep-size $EP_SIZE \
+--quantization modelopt_fp4 --fp4-gemm-backend flashinfer_cutlass \
+--kv-cache-dtype fp8_e4m3 \
+--mamba-ssm-dtype bfloat16 \
+--cuda-graph-max-bs $CUDA_GRAPH_MAX_BATCH_SIZE --max-running-requests $MAX_RUNNING_REQUESTS \
+--mem-fraction-static $MEM_FRAC_STATIC --chunked-prefill-size $CHUNKED_PREFILL_SIZE --max-prefill-tokens $MAX_PREFILL_TOKENS \
+--context-length $CONTEXT_LENGTH --disable-radix-cache \
+--attention-backend trtllm_mha --moe-runner-backend flashinfer_trtllm \
+$EXTRA_ARGS --scheduler-recv-interval $SCHEDULER_RECV_INTERVAL \
+--tokenizer-worker-num 6 --stream-interval 30 > $SERVER_LOG 2>&1 &
+
+SERVER_PID=$!
+
+# Wait for server to be ready
+wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
+
+pip install -q datasets pandas
+
+run_benchmark_serving \
+    --model "$MODEL" \
+    --port "$PORT" \
+    --backend vllm \
+    --input-len "$ISL" \
+    --output-len "$OSL" \
+    --random-range-ratio "$RANDOM_RANGE_RATIO" \
+    --num-prompts "$((CONC * 10))" \
+    --max-concurrency "$CONC" \
+    --result-filename "$RESULT_FILENAME" \
+    --result-dir /workspace/
+
+# After throughput, run evaluation only if RUN_EVAL is true
+if [ "${RUN_EVAL}" = "true" ]; then
+    run_eval --framework lm-eval --port "$PORT"
+    append_lm_eval_summary
+fi
+
+# Stop GPU monitoring
+stop_gpu_monitor
+set +x
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index b3720abc8..5a35d3914 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -1198,3 +1198,12 @@
   description:
     - "Add --disable-radix-cache to SGLang server launch command for qwen3.5 MI300X and MI325X benchmark scripts"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/970
+
+- config-keys:
+    - qwen3.5-fp4-b200-sglang
+  description:
+    - "Add Qwen3.5-397B-A17B NVFP4 B200 SGLang benchmark config and launch script"
+    - "Image: lmsysorg/sglang:v0.5.9-cu129-amd64"
+    - "Model: nvidia/Qwen3.5-397B-A17B-NVFP4"
+    - "Configs: 1k1k (TP4 conc 4-128), 8k1k (TP4 conc 4-128)"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/820