diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml
index 5a0e6a636..30349ab8d 100644
--- a/.github/configs/nvidia-master.yaml
+++ b/.github/configs/nvidia-master.yaml
@@ -11848,6 +11848,34 @@ qwen3.5-fp8-h100-sglang-agentic:
       - { tp: 8, ep: 8, offloading: none,    conc-list: [1, 2, 4, 8, 12, 14, 16] }
       - { tp: 8, ep: 8, offloading: hicache, conc-list: [12, 14, 16, 20, 24, 28, 32, 42] }
 
+minimaxm3-fp4-b200-dynamo-vllm:
+  image: vllm/vllm-openai:vllm-minimax-m3-perf-x86_64-13.0.1-8b00f41
+  model: nvidia/MiniMax-M3-NVFP4
+  model-prefix: minimaxm3
+  runner: b200-multinode
+  precision: fp4
+  framework: dynamo-vllm
+  multinode: true
+  disagg: true
+  scenarios:
+    fixed-seq-len:
+    - isl: 8192
+      osl: 1024
+      search-space:
+      - conc-list: [2048]
+        prefill:
+          num-worker: 2
+          tp: 2
+          ep: 2
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/vllm/minimax-m3/b200-fp4/8k1k/2p1d-dep2-dep8-8k1k.yaml"
+        decode:
+          num-worker: 1
+          tp: 8
+          ep: 8
+          dp-attn: true
+
 minimaxm3-fp8-b300-dynamo-vllm:
   image: vllm/vllm-openai:minimax-m3-0618-x86_64-cu130
   model: MiniMaxAI/MiniMax-M3-MXFP8
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/2p1d-dep2-dep8-8k1k.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/2p1d-dep2-dep8-8k1k.yaml
new file mode 100644
index 000000000..f89a8ab9d
--- /dev/null
+++ b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/2p1d-dep2-dep8-8k1k.yaml
@@ -0,0 +1,85 @@
+name: "minimax-m3-vllm-disagg-b200-2p1d-fp4-dep2-dep8-8k1k"
+
+model:
+  path: "nvidia/MiniMax-M3-NVFP4"
+  container: "vllm/vllm-openai:vllm-minimax-m3-perf-x86_64-13.0.1-8b00f41"
+  precision: "fp4"
+
+resources:
+  gpu_type: "b200"
+  gpus_per_node: 8
+  prefill_nodes: 1
+  decode_nodes: 1
+  prefill_workers: 2
+  decode_workers: 1
+  gpus_per_prefill: 2
+  gpus_per_decode: 8
+
+dynamo:
+  install: true
+  version: 1.3.0.dev20260614
+
+frontend:
+  type: dynamo
+  enable_multiple_frontends: false
+
+backend:
+  type: vllm
+  connector: null
+
+  prefill_environment:
+    VLLM_FLOAT32_MATMUL_PRECISION: high
+    UCX_TLS: "cuda_copy,rc"
+
+  decode_environment:
+    VLLM_FLOAT32_MATMUL_PRECISION: high
+    UCX_TLS: "cuda_copy,rc"
+
+  vllm_config:
+    prefill:
+      no-enable-flashinfer-autotune: true
+      tensor-parallel-size: 1
+      data-parallel-size: 2
+      data-parallel-rpc-port: 13345
+      enable-expert-parallel: true
+      trust-remote-code: true
+      no-enable-prefix-caching: true
+      kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
+      attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8"}'
+      kv-cache-dtype: fp8
+      block-size: 128
+      gpu-memory-utilization: 0.90
+      max-model-len: 9472
+      language-model-only: true
+      stream-interval: 32
+
+    decode:
+      no-enable-flashinfer-autotune: true
+      tensor-parallel-size: 1
+      data-parallel-size: 8
+      data-parallel-rpc-port: 13345
+      enable-expert-parallel: true
+      trust-remote-code: true
+      no-enable-prefix-caching: true
+      kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
+      attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8"}'
+      kv-cache-dtype: fp8
+      block-size: 128
+      gpu-memory-utilization: 0.90
+      max-model-len: 9472
+      language-model-only: true
+      stream-interval: 32
+      max-num-seqs: 1024  # One DP8 decode worker provides 8 DP ranks.
+      max-num-batched-tokens: 16384
+      max-cudagraph-capture-size: 4096
+
+health_check:
+  max_attempts: 360
+  interval_seconds: 10
+
+benchmark:
+  type: "sa-bench"
+  isl: 8192
+  osl: 1024
+  concurrencies: "2048"
+  req_rate: "inf"
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 3d89fa688..52801fdee 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -4407,3 +4407,11 @@
   description:
     - "Bump SGLang image from lmsysorg/sglang:deepseek-v4-blackwell (digest sha256:df18bfc4...) to mainline nightly lmsysorg/sglang:nightly-dev-cu13-20260628-da802ddc."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1923
+
+- config-keys:
+    - minimaxm3-fp4-b200-dynamo-vllm
+  description:
+    - "Add MiniMax-M3 NVFP4 B200 Dynamo-vLLM disaggregated 8k1k configuration at concurrency 2048."
+    - "Port the B300 4P2D DEP2/DEP8 recipe to a B200 2P1D topology using one prefill node and one decode node."
+    - "Use the b200-multinode runner and vllm/vllm-openai:vllm-minimax-m3-perf-x86_64-13.0.1-8b00f41; omit max-cudagraph-capture-size and max-num-batched-tokens from prefill."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1982
diff --git a/runners/launch_b200-dgxc.sh b/runners/launch_b200-dgxc.sh
index f10e0f4ea..8e915061e 100644
--- a/runners/launch_b200-dgxc.sh
+++ b/runners/launch_b200-dgxc.sh
@@ -113,6 +113,12 @@ if [[ "$IS_MULTINODE" == "true" ]]; then
         git checkout aflowers/vllm-gb200-v0.20.0
         mkdir -p recipes/vllm/deepseek-v4
         cp -rT "$GITHUB_WORKSPACE/benchmarks/multi_node/srt-slurm-recipes/vllm/deepseek-v4" recipes/vllm/deepseek-v4
+    elif [[ $FRAMEWORK == "dynamo-vllm" && $MODEL_PREFIX == "minimaxm3" && $PRECISION == "fp4" ]]; then
+        git clone https://github.com/NVIDIA/srt-slurm.git "$SRT_REPO_DIR"
+        cd "$SRT_REPO_DIR" || exit 1
+        git checkout main
+        mkdir -p recipes/vllm/minimax-m3/b200-fp4
+        cp -rT "$GITHUB_WORKSPACE/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4" recipes/vllm/minimax-m3/b200-fp4
     elif [[ $FRAMEWORK == "dynamo-vllm" && $MODEL_PREFIX == "minimaxm2.5" && $PRECISION == "fp4" ]]; then
         git clone https://github.com/NVIDIA/srt-slurm.git "$SRT_REPO_DIR"
         cd "$SRT_REPO_DIR" || exit 1