diff --git a/benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_b200.sh b/benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_b200.sh
index 49ab8df755..16041a2ea4 100755
--- a/benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_b200.sh
+++ b/benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_b200.sh
@@ -45,7 +45,7 @@ if [ "${DP_ATTENTION}" = "true" ]; then
 elif [ "$EP_SIZE" -gt 1 ]; then
   PARALLEL_ARGS="--tensor-parallel-size=$TP --enable-expert-parallel"
 else
-  PARALLEL_ARGS="--tensor-parallel-size=$TP"
+  PARALLEL_ARGS="--tensor-parallel-size=$TP --moe-backend marlin"
 fi
 
 if [ "${EVAL_ONLY}" = "true" ]; then
diff --git a/benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_b200_mtp.sh b/benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_b200_mtp.sh
index dde0e69c0f..54aabd3422 100644
--- a/benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_b200_mtp.sh
+++ b/benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_b200_mtp.sh
@@ -68,7 +68,7 @@ if [ "${DP_ATTENTION}" = "true" ]; then
 elif [ "$EP_SIZE" -gt 1 ]; then
   PARALLEL_ARGS="--tensor-parallel-size=$TP --enable-expert-parallel"
 else
-  PARALLEL_ARGS="--tensor-parallel-size=$TP"
+  PARALLEL_ARGS="--tensor-parallel-size=$TP --moe-backend marlin"
 fi
 
 # use 3 speculative tokens for all configs for now
diff --git a/benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_b300.sh b/benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_b300.sh
index 53dd5a5123..1f4187c044 100755
--- a/benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_b300.sh
+++ b/benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_b300.sh
@@ -53,7 +53,7 @@ if [ "${DP_ATTENTION}" = "true" ]; then
 elif [ "$EP_SIZE" -gt 1 ]; then
   PARALLEL_ARGS="--tensor-parallel-size=$TP --enable-expert-parallel"
 else
-  PARALLEL_ARGS="--tensor-parallel-size=$TP"
+  PARALLEL_ARGS="--tensor-parallel-size=$TP --moe-backend marlin"
 fi
 
 if [ "${EVAL_ONLY}" = "true" ]; then
diff --git a/benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_b300_mtp.sh b/benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_b300_mtp.sh
index a93da87b0f..742933deb1 100644
--- a/benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_b300_mtp.sh
+++ b/benchmarks/single_node/fixed_seq_len/minimaxm3_fp8_b300_mtp.sh
@@ -69,7 +69,7 @@ if [ "${DP_ATTENTION}" = "true" ]; then
 elif [ "$EP_SIZE" -gt 1 ]; then
   PARALLEL_ARGS="--tensor-parallel-size=$TP --enable-expert-parallel"
 else
-  PARALLEL_ARGS="--tensor-parallel-size=$TP"
+  PARALLEL_ARGS="--tensor-parallel-size=$TP --moe-backend marlin"
 fi
 
 # use 3 speculative tokens for all configs for now
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 1a7eb91e38..488d144de2 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -3900,3 +3900,12 @@
   description:
     - "Add Qwen3.5-397B-A17B-NVFP4 B200 single-node TensorRT-LLM benchmark (1k/1k and 8k/1k) with a TP/TEP/DEP parallelism sweep"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1711
+
+- config-keys:
+    - minimaxm3-fp8-b200-vllm
+    - minimaxm3-fp8-b300-vllm
+    - minimaxm3-fp8-b200-vllm-mtp
+    - minimaxm3-fp8-b300-vllm-mtp
+  description:
+    - "Use the Marlin MoE backend for MiniMax-M3 B200/B300 TP-only vLLM configurations by adding --moe-backend marlin when expert parallelism is disabled."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1809