diff --git a/tests/integration/defs/accuracy/accuracy_core.py b/tests/integration/defs/accuracy/accuracy_core.py
index d9c9980d5e61..1ff754f97342 100644
--- a/tests/integration/defs/accuracy/accuracy_core.py
+++ b/tests/integration/defs/accuracy/accuracy_core.py
@@ -434,6 +434,9 @@ def convert(self):
             f"--dtype={self.dtype}",
         ]
 
+        if "nemotron_nas" in self.EXAMPLE_FOLDER:
+            convert_cmd.append("--trust_remote_code")
+
         if self.MODEL_FORMAT == "NEMO":
             convert_cmd.append(f"--nemo_ckpt_path={self.MODEL_PATH}")
         else:
diff --git a/tests/integration/defs/accuracy/references/gpqa_diamond.yaml b/tests/integration/defs/accuracy/references/gpqa_diamond.yaml
index 3fccc693227e..9e4e988f335d 100644
--- a/tests/integration/defs/accuracy/references/gpqa_diamond.yaml
+++ b/tests/integration/defs/accuracy/references/gpqa_diamond.yaml
@@ -16,3 +16,5 @@ deepseek-ai/DeepSeek-R1:
     accuracy: 70.45
 nvidia/Llama-3_3-Nemotron-Super-49B-v1:
   - accuracy: 44.95
+  - quant_algo: FP8
+    accuracy: 49.49
diff --git a/tests/integration/defs/accuracy/references/gsm8k.yaml b/tests/integration/defs/accuracy/references/gsm8k.yaml
index a19abf12e8d3..9748b122bcd1 100644
--- a/tests/integration/defs/accuracy/references/gsm8k.yaml
+++ b/tests/integration/defs/accuracy/references/gsm8k.yaml
@@ -65,5 +65,7 @@ Qwen3/Qwen3-30B-A3B:
     accuracy: 83.43
 nvidia/Llama-3_3-Nemotron-Super-49B-v1:
   - accuracy: 92.57
+  - quant_algo: FP8
+    accuracy: 92.42
 nvidia/Nemotron-H-8B-Base-8K:
   - accuracy: 46.20
diff --git a/tests/integration/defs/accuracy/references/mmlu.yaml b/tests/integration/defs/accuracy/references/mmlu.yaml
index 51c1cdd69ea1..4380b799764b 100644
--- a/tests/integration/defs/accuracy/references/mmlu.yaml
+++ b/tests/integration/defs/accuracy/references/mmlu.yaml
@@ -121,6 +121,8 @@ Qwen3/Qwen3-30B-A3B:
     accuracy: 80.65
 nvidia/Llama-3_3-Nemotron-Super-49B-v1:
   - accuracy: 79.43
+  - quant_algo: FP8
+    accuracy: 79.26
 nvidia/Llama-3.1-Nemotron-Nano-8B-v1:
   - accuracy: 57.97
 nvidia/Nemotron-H-8B-Base-8K:
diff --git a/tests/integration/defs/accuracy/test_cli_flow.py b/tests/integration/defs/accuracy/test_cli_flow.py
index e9fdac5dcbec..2ba3cf657dc3 100644
--- a/tests/integration/defs/accuracy/test_cli_flow.py
+++ b/tests/integration/defs/accuracy/test_cli_flow.py
@@ -200,6 +200,30 @@ def test_fp8_prequantized(self, mocker):
         self.run(quant_algo=QuantAlgo.FP8, kv_cache_quant_algo=QuantAlgo.FP8)
 
 
+# TODO: Remove the CLI tests once NIMs use PyTorch backend
+class TestLlama3_3NemotronSuper49Bv1(CliFlowAccuracyTestHarness):
+    MODEL_NAME = "nvidia/Llama-3_3-Nemotron-Super-49B-v1"
+    MODEL_PATH = f"{llm_models_root()}/nemotron-nas/Llama-3_3-Nemotron-Super-49B-v1"
+    EXAMPLE_FOLDER = "models/core/nemotron_nas"
+
+    @pytest.mark.skip_less_device(2)
+    def test_auto_dtype_tp2(self):
+        self.run(tasks=[MMLU(self.MODEL_NAME)], tp_size=2, dtype='auto')
+
+    @pytest.mark.skip(
+        reason="nemotron-nas scripts have to accommodate fp8 flags")
+    @pytest.mark.skip_less_device(2)
+    @pytest.mark.skip_device_not_contain(["H100", "B200"])
+    def test_fp8_prequantized_tp2(self, mocker):
+        mocker.patch.object(
+            self.__class__, "MODEL_PATH",
+            f"{llm_models_root()}/nemotron-nas/Llama-3_3-Nemotron-Super-49B-v1-FP8"
+        )
+        self.run(tasks=[MMLU(self.MODEL_NAME)],
+                 tp_size=2,
+                 quant_algo=QuantAlgo.FP8)
+
+
 class TestPhi2(CliFlowAccuracyTestHarness):
     MODEL_NAME = "microsoft/phi-2"
     MODEL_PATH = f"{llm_models_root()}/phi-2"
diff --git a/tests/integration/defs/accuracy/test_llm_api_pytorch.py b/tests/integration/defs/accuracy/test_llm_api_pytorch.py
index ad8b59eec5c8..3156782e977c 100644
--- a/tests/integration/defs/accuracy/test_llm_api_pytorch.py
+++ b/tests/integration/defs/accuracy/test_llm_api_pytorch.py
@@ -891,7 +891,7 @@ def test_auto_dtype_tp8(self):
             task.evaluate(llm)
 
 
-class TestNemotronSuper(LlmapiAccuracyTestHarness):
+class TestLlama3_3NemotronSuper49Bv1(LlmapiAccuracyTestHarness):
     MODEL_NAME = "nvidia/Llama-3_3-Nemotron-Super-49B-v1"
     MODEL_PATH = f"{llm_models_root()}/nemotron-nas/Llama-3_3-Nemotron-Super-49B-v1"
 
@@ -906,6 +906,20 @@ def test_auto_dtype_tp2(self):
             task.evaluate(llm,
                           extra_evaluator_kwargs=dict(apply_chat_template=True))
 
+    @pytest.mark.skip_less_device(2)
+    @pytest.mark.skip_device_not_contain(["H100", "B200"])
+    def test_fp8_prequantized_tp2(self):
+        model_path = f"{llm_models_root()}/nemotron-nas/Llama-3_3-Nemotron-Super-49B-v1-FP8"
+        with LLM(model_path, tensor_parallel_size=2) as llm:
+            assert llm.args.quant_config.quant_algo == QuantAlgo.FP8
+            task = MMLU(self.MODEL_NAME)
+            task.evaluate(llm)
+            task = GSM8K(self.MODEL_NAME)
+            task.evaluate(llm)
+            task = GPQADiamond(self.MODEL_NAME)
+            task.evaluate(llm,
+                          extra_evaluator_kwargs=dict(apply_chat_template=True))
+
 
 class TestNemotronNano(LlmapiAccuracyTestHarness):
     MODEL_NAME = "nvidia/Llama-3.1-Nemotron-Nano-8B-v1"
diff --git a/tests/integration/test_lists/qa/examples_test_list.txt b/tests/integration/test_lists/qa/examples_test_list.txt
index 6dd0b6c834f2..b6f31c083cd5 100644
--- a/tests/integration/test_lists/qa/examples_test_list.txt
+++ b/tests/integration/test_lists/qa/examples_test_list.txt
@@ -445,7 +445,10 @@ accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_fp8_block_scales[mtp_
 accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=False]
 accuracy/test_llm_api_pytorch.py::TestMinitron4BBaseInstruct::test_fp8_prequantized
 accuracy/test_llm_api_pytorch.py::TestNemotronNas::test_auto_dtype_tp8
-accuracy/test_llm_api_pytorch.py::TestNemotronSuper::test_auto_dtype_tp2
+accuracy/test_llm_api_pytorch.py::TestLlama3_3NemotronSuper49Bv1::test_auto_dtype_tp2
+accuracy/test_llm_api_pytorch.py::TestLlama3_3NemotronSuper49Bv1::test_fp8_prequantized_tp2
+accuracy/test_cli_flow.py::TestLlama3_3NemotronSuper49Bv1::test_auto_dtype_tp2
+accuracy/test_cli_flow.py::TestLlama3_3NemotronSuper49Bv1::test_fp8_prequantized_tp2
 accuracy/test_llm_api_pytorch.py::TestNemotronNano::test_auto_dtype
 accuracy/test_llm_api_pytorch.py::TestNemotronH::test_auto_dtype
 accuracy/test_llm_api_pytorch.py::TestQwen2_7BInstruct::test_auto_dtype
diff --git a/tests/integration/test_lists/qa/llm_sanity_test.txt b/tests/integration/test_lists/qa/llm_sanity_test.txt
index d174a0a1cfc6..e79a38e73ed5 100644
--- a/tests/integration/test_lists/qa/llm_sanity_test.txt
+++ b/tests/integration/test_lists/qa/llm_sanity_test.txt
@@ -136,7 +136,8 @@ accuracy/test_llm_api_pytorch.py::TestLlama4ScoutInstruct::test_auto_dtype[tp8-c
 accuracy/test_llm_api_pytorch.py::TestMixtral8x7B::test_fp8_tp2
 accuracy/test_llm_api_pytorch.py::TestMixtral8x7B::test_nvfp4_tp2
 accuracy/test_llm_api_pytorch.py::TestNemotronNas::test_auto_dtype_tp8
-accuracy/test_llm_api_pytorch.py::TestNemotronSuper::test_auto_dtype_tp2
+accuracy/test_llm_api_pytorch.py::TestLlama3_3NemotronSuper49Bv1::test_auto_dtype_tp2
+accuracy/test_cli_flow.py::TestLlama3_3NemotronSuper49Bv1::test_auto_dtype_tp2
 accuracy/test_llm_api_pytorch.py::TestNemotronNano::test_auto_dtype
 accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=0-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=False]
 accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_fp8_block_scales[mtp_nextn=0-fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=False]