diff --git a/tests/integration/test_lists/qa/llm_perf_core.yml b/tests/integration/test_lists/qa/llm_perf_core.yml
index bdf71033294d..8bb7ead14921 100644
--- a/tests/integration/test_lists/qa/llm_perf_core.yml
+++ b/tests/integration/test_lists/qa/llm_perf_core.yml
@@ -13,6 +13,7 @@ llm_perf_core:
 # 8: B300 test cases
 # 9: H100, H20, B200, B300, RTX6000-Server test cases
 # 10: H20, B200, B300, RTX6000-Server test cases
+# 10b: H20, B200, B300 test cases (>120G per GPU; excludes 96G RTX6000-Server)
 # 11: RTX-6000 Server test cases
 # ===============================================================================
 
@@ -304,7 +305,9 @@ llm_perf_core:
         lte: 12.0
   tests:
   #qwen3.5_397b_a17b_fp8 (MoE FP8 380G, 8-GPU ep=8)
-  - perf/test_perf.py::test_perf[qwen3.5_397b_a17b_fp8-bench-pytorch-float8-input_output_len:128,128-ep:8-tp:8-gpus:8]
+  # 128,128 is a trivial workload but the 380G checkpoint load alone exceeds the
+  # 60min default on the slower platforms in this condition.
+  - perf/test_perf.py::test_perf[qwen3.5_397b_a17b_fp8-bench-pytorch-float8-input_output_len:128,128-ep:8-tp:8-gpus:8] TIMEOUT(120)
   - perf/test_perf.py::test_perf[qwen3.5_397b_a17b_fp8-bench-pytorch-float8-input_output_len:500,2000-ep:8-tp:8-gpus:8]
   - perf/test_perf.py::test_perf[qwen3.5_397b_a17b_fp8-bench-pytorch-float8-input_output_len:2000,500-ep:8-tp:8-gpus:8]
   - perf/test_perf.py::test_perf[qwen3.5_397b_a17b_fp8-bench-pytorch-float8-input_output_len:8000,1000-ep:8-tp:8-gpus:8]
@@ -323,9 +326,6 @@ llm_perf_core:
       gpu_memory:
         gt: 90000
   tests:
-  # deepseek_r1_0528
-  - perf/test_perf.py::test_perf[deepseek_r1_0528_fp8-bench-pytorch-float8-input_output_len:8000,1000-reqs:20000-ep:8-tp:8-gpus:8] TIMEOUT(120)
-  - perf/test_perf.py::test_perf[deepseek_r1_0528_fp8-bench-pytorch-float8-input_output_len:1000,2000-reqs:3000-ep:8-tp:8-gpus:8] TIMEOUT(100)
   #qwen3.5_122b_a10b (MoE BF16 234G, 4-GPU): OOM on 80G GPUs, needs >90G
   - perf/test_perf.py::test_perf[qwen3.5_122b_a10b-bench-pytorch-bfloat16-input_output_len:128,128-ep:4-tp:4-gpus:4]
   - perf/test_perf.py::test_perf[qwen3.5_122b_a10b-bench-pytorch-bfloat16-input_output_len:500,2000-ep:4-tp:4-gpus:4]
@@ -338,6 +338,25 @@ llm_perf_core:
   - perf/test_perf.py::test_perf[qwen3.5_397b_a17b_fp4-bench-pytorch-float4-maxbs:1-input_output_len:8000,1000-reqs:10-con:1-ep:8-tp:8-gpus:8] #min_latency
   - perf/test_perf.py::test_perf[qwen3.5_397b_a17b_fp4-bench-pytorch-float4-maxbs:512-input_output_len:8000,1000-con:512-ep:8-tp:8-gpus:8] #max_throughput
 
+
+# 10b: H20, B200, B300 test cases - same as 10 but excludes 96G-per-GPU parts.
+# These checkpoints are ~645G, i.e. ~81G/GPU of weights at tp:8, which leaves
+# only ~14G per GPU for KV cache, activations and comm buffers on a 96G part.
+- condition:
+    ranges:
+      system_gpu_count:
+        gte: 8
+      compute_capability:
+        gte: 9.0
+        lte: 12.0
+      gpu_memory:
+        gt: 120000
+  tests:
+  # deepseek_r1_0528 (FP8 645G, 8-GPU ep=8)
+  - perf/test_perf.py::test_perf[deepseek_r1_0528_fp8-bench-pytorch-float8-input_output_len:8000,1000-reqs:20000-ep:8-tp:8-gpus:8] TIMEOUT(120)
+  - perf/test_perf.py::test_perf[deepseek_r1_0528_fp8-bench-pytorch-float8-input_output_len:1000,2000-reqs:3000-ep:8-tp:8-gpus:8] TIMEOUT(100)
+
+
 # 11: RTX-6000 Server test cases
 - condition:
     ranges:
@@ -347,7 +366,9 @@ llm_perf_core:
         gte: 12.0
         lte: 12.0
   tests:
-  - perf/test_perf.py::test_perf[qwen3_235b_a22b_fp4-bench-pytorch-float4-input_output_len:1000,2000-con:8-ep:8-tp:8-gpus:8]
+  # con:8 keeps the GPUs far from saturation, so wall time is dominated by the
+  # 2000-token decode of each request; does not fit the 60min default here.
+  - perf/test_perf.py::test_perf[qwen3_235b_a22b_fp4-bench-pytorch-float4-input_output_len:1000,2000-con:8-ep:8-tp:8-gpus:8] TIMEOUT(120)
   - perf/test_perf.py::test_perf[qwen3_235b_a22b_fp4-bench-pytorch-float4-input_output_len:1000,2000-con:512-ep:8-tp:8-gpus:8]
   # deepseek_r1_0528
   - perf/test_perf.py::test_perf[deepseek_r1_0528_fp4-bench-pytorch-float4-maxbs:1-input_output_len:1000,2000-reqs:10-ep:4-tp:8-gpus:8] TIMEOUT(120)