diff --git a/tools/launcher/examples/Nemotron-h/NVIDIA-Nemotron-3-Super-120B-A12B-BF16/specdec_bench_mtp_vllm.yaml b/tools/launcher/examples/Nemotron-h/NVIDIA-Nemotron-3-Super-120B-A12B-BF16/specdec_bench_mtp_vllm.yaml
new file mode 100644
index 00000000000..1107c074605
--- /dev/null
+++ b/tools/launcher/examples/Nemotron-h/NVIDIA-Nemotron-3-Super-120B-A12B-BF16/specdec_bench_mtp_vllm.yaml
@@ -0,0 +1,73 @@
+# SPEED-bench MTP speculative-decoding run for NVIDIA-Nemotron-3-Super-120B-A12B-BF16 via vLLM.
+#
+# Nemotron-3-Super-120B-A12B is 120B total params (MoE; 12B active per
+# token). BF16 weights = 240 GB total, so tp_size=4 minimum on 80 GB
+# H100/A100.
+#
+# Slurm run on cw_dfw — cells override per-cell knobs via
+# pipeline.task_N.args+=[...]:
+#
+#   uv run slurm.py \
+#     --yaml modules/Model-Optimizer/tools/launcher/examples/Nemotron-h/NVIDIA-Nemotron-3-Super-120B-A12B-BF16/specdec_bench_mtp_vllm.yaml \
+#     --yes detach=true \
+#     pipeline.task_0.args+=["--temperature 0","--max_seq_len 65536","--save_dir /scratchspace/<sweep>/qualitative","--draft_length 3"] \
+#     pipeline.task_1.args+=["--temperature 0","--max_seq_len 65536","--save_dir /scratchspace/<sweep>/throughput_32k","--num_requests 80","--draft_length 3"]
+
+job_name: NVIDIA-Nemotron-3-Super-120B-A12B-BF16_specdec_bench_mtp_vllm
+
+pipeline:
+  global_vars:
+    hf_model: /hf-local/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
+
+  # task_0: SPEED qualitative split
+  task_0:
+    script: common/specdec_bench/run.sh
+    args:
+      - --dataset speed
+      - --dataset_path /hf-local/nvidia/SPEED-Bench-Internal/qualitative
+      - --engine VLLM
+      - --speculative_algorithm MTP
+      - --draft_length 3
+      - --tp_size 4
+      - --ep_size 1
+      - --concurrency 32
+      - --output_length 4096
+      - --aa_timing
+      - --show_progress
+      - --save_dir /scratchspace/{sweep_name_default}/qualitative
+    environment:
+      - HF_MODEL_CKPT: <<global_vars.hf_model>>
+      - HF_LOCAL: /hf-local
+    slurm_config:
+      _factory_: "slurm_factory"
+      nodes: 1
+      ntasks_per_node: 1
+      gpus_per_node: 4
+      container: vllm/vllm-openai:v0.22.1
+
+  # task_1: SPEED throughput_32k split
+  task_1:
+    script: common/specdec_bench/run.sh
+    args:
+      - --dataset speed
+      - --dataset_path /hf-local/nvidia/SPEED-Bench-Internal/throughput_32k
+      - --engine VLLM
+      - --speculative_algorithm MTP
+      - --draft_length 3
+      - --tp_size 4
+      - --ep_size 1
+      - --concurrency 8
+      - --num_requests 80
+      - --output_length 4096
+      - --aa_timing
+      - --show_progress
+      - --save_dir /scratchspace/{sweep_name_default}/throughput_32k
+    environment:
+      - HF_MODEL_CKPT: <<global_vars.hf_model>>
+      - HF_LOCAL: /hf-local
+    slurm_config:
+      _factory_: "slurm_factory"
+      nodes: 1
+      ntasks_per_node: 1
+      gpus_per_node: 4
+      container: vllm/vllm-openai:v0.22.1