diff --git a/.github/workflows/nightly-benchmark.yml b/.github/workflows/nightly-benchmark.yml
index a7f12a0b68..e6012ede2c 100644
--- a/.github/workflows/nightly-benchmark.yml
+++ b/.github/workflows/nightly-benchmark.yml
@@ -121,6 +121,9 @@ jobs:
           - { id: Qwen/Qwen2.5-7B-Instruct, slug: Qwen-Qwen2.5-7B-Instruct, test_class: TestNightlyQwen7bSingle }
           - { id: Qwen/Qwen3-30B-A3B, slug: Qwen-Qwen3-30B-A3B, test_class: TestNightlyQwen30bSingle }
           - { id: openai/gpt-oss-20b, slug: openai-gpt-oss-20b, test_class: TestNightlyGptOss20bSingle }
+          - { id: meta-llama/Llama-4-Scout-17B-16E-Instruct, slug: meta-llama-Llama-4-Scout-17B-16E-Instruct, test_class: TestNightlyLlama4ScoutSingle }
+          - { id: meta-llama/Llama-3.3-70B-Instruct, slug: meta-llama-Llama-3.3-70B-Instruct, test_class: TestNightlyLlama70bSingle }
+          - { id: RedHatAI/Llama-3.3-70B-Instruct-FP8-dynamic, slug: RedHatAI-Llama-3.3-70B-Instruct-FP8-dynamic, test_class: TestNightlyLlama70bFp8Single }
         variant:
           - { id: sglang, runtime: sglang, grpc_only: "false", setup_vllm: false, setup_trtllm: false }
           - { id: vllm,   runtime: vllm,   grpc_only: "false", setup_vllm: true, setup_trtllm: false }
diff --git a/e2e_test/benchmarks/test_nightly_perf.py b/e2e_test/benchmarks/test_nightly_perf.py
index ef439eebb3..51b3d290a0 100644
--- a/e2e_test/benchmarks/test_nightly_perf.py
+++ b/e2e_test/benchmarks/test_nightly_perf.py
@@ -109,6 +109,27 @@ def _run_nightly(setup_backend, genai_bench_runner, model_id, worker_count=1, **
         ["http", "grpc"],
         {},
     ),
+    (
+        "meta-llama/Llama-4-Scout-17B-16E-Instruct",
+        "Llama4Scout",
+        1,
+        ["http", "grpc"],
+        {},
+    ),
+    (
+        "meta-llama/Llama-3.3-70B-Instruct",
+        "Llama70b",
+        1,
+        ["http", "grpc"],
+        {},
+    ),
+    (
+        "RedHatAI/Llama-3.3-70B-Instruct-FP8-dynamic",
+        "Llama70bFp8",
+        1,
+        ["http", "grpc"],
+        {},
+    ),
 ]
 
 
diff --git a/e2e_test/infra/model_specs.py b/e2e_test/infra/model_specs.py
index 31ec82591b..64ee4ee1f5 100644
--- a/e2e_test/infra/model_specs.py
+++ b/e2e_test/infra/model_specs.py
@@ -102,14 +102,6 @@ def _resolve_model_path(hf_path: str) -> str:
         "tp": 1,
         "features": ["chat", "streaming", "multimodal"],
     },
-    # Llama-4-Scout (17B with 16 experts) - Multimodal tests
-    "meta-llama/Llama-4-Scout-17B-16E-Instruct": {
-        "model": _resolve_model_path("meta-llama/Llama-4-Scout-17B-16E-Instruct"),
-        "tp": 4,
-        "features": ["chat", "streaming", "multimodal", "moe"],
-        "vllm_args": ["--max-model-len", "196608"],
-        "startup_timeout": 1200,
-    },
     # Llama-4-Maverick (17B with 128 experts, FP8) - Nightly benchmarks
     "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": {
         "model": _resolve_model_path("meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8"),
@@ -126,6 +118,52 @@ def _resolve_model_path(hf_path: str) -> str:
             "--max-model-len=163840",  # 160K context length (vLLM)
             "--attention-backend=FLASHINFER",  # FLASHINFER attention backend
         ],
+        "startup_timeout": 1200,  # Large MoE model may need extra download/load time
+    },
+    # Llama-4-Scout (17B with 16 experts) - Nightly benchmarks and Multimodal tests
+    "meta-llama/Llama-4-Scout-17B-16E-Instruct": {
+        "model": _resolve_model_path("meta-llama/Llama-4-Scout-17B-16E-Instruct"),
+        "tp": 4,
+        "features": ["chat", "streaming", "function_calling", "multimodal", "moe"],
+        "worker_args": [
+            "--context-length=196608",
+            "--attention-backend=fa3",
+            "--cuda-graph-max-bs=256",
+            "--max-running-requests=300",
+            "--mem-fraction-static=0.85",
+        ],
+        "vllm_args": [
+            "--max-model-len=196608",
+        ],
+        "startup_timeout": 1200,  # Large MoE model may need extra download/load time
+    },
+    # Llama-3.3-70B - Nightly benchmarks
+    "meta-llama/Llama-3.3-70B-Instruct": {
+        "model": _resolve_model_path("meta-llama/Llama-3.3-70B-Instruct"),
+        "tp": 4,
+        "features": ["chat", "streaming", "function_calling"],
+        "worker_args": [
+            "--mem-fraction-static=0.9",
+        ],
+        "vllm_args": [
+            "--max-model-len=131072",
+            "--gpu-memory-utilization=0.9",
+            "--enable-chunked-prefill",
+        ],
+    },
+    # Llama-3.3-70B FP8 - Nightly benchmarks
+    "RedHatAI/Llama-3.3-70B-Instruct-FP8-dynamic": {
+        "model": _resolve_model_path("RedHatAI/Llama-3.3-70B-Instruct-FP8-dynamic"),
+        "tp": 4,
+        "features": ["chat", "streaming", "function_calling"],
+        "worker_args": [
+            "--mem-fraction-static=0.9",
+        ],
+        "vllm_args": [
+            "--max-model-len=131072",
+            "--gpu-memory-utilization=0.9",
+            "--enable-chunked-prefill",
+        ],
     },
 }