NVIDIA · ericksoa · Aug 7, 2026 · Aug 7, 2026 · Aug 7, 2026 · Aug 7, 2026
diff --git a/ci/platform-matrix.json b/ci/platform-matrix.json
@@ -47,7 +47,7 @@
       "status": "tested",
       "prd_priority": "P1",
       "ci_tested": true,
-      "notes": "Use the standard installer and `$$nemoclaw onboard`. The automatic two-DGX Spark managed-vLLM profile is Experimental, and physical two-node end-to-end validation is pending. For the profile requirements and controls, see [Set Up vLLM on Two DGX Sparks](../inference/local-inference/set-up-vllm-on-two-dgx-sparks). For the validated single-DGX Spark walkthrough with local inference, see the [NVIDIA Spark playbook](https://build.nvidia.com/spark/nemoclaw)."
+      "notes": "Use the standard installer and `$$nemoclaw onboard`. DGX Spark Express keeps automatic managed-vLLM serving-profile selection as option 1 and offers the fixed single-host catalog profile as option 2. The automatic two-DGX Spark managed-vLLM profile is Experimental, and physical two-node end-to-end validation is pending. For the profile requirements and controls, see [Set Up vLLM on Two DGX Sparks](../inference/local-inference/set-up-vllm-on-two-dgx-sparks). For the validated single-DGX Spark walkthrough with local inference, see the [NVIDIA Spark playbook](https://build.nvidia.com/spark/nemoclaw)."
     },
     {
       "name": "Windows WSL2",

diff --git a/docs/get-started/prerequisites.mdx b/docs/get-started/prerequisites.mdx
@@ -101,7 +101,7 @@ The table comes from [`ci/platform-matrix.json`](https://github.com/NVIDIA/NemoC
 {/* platform-matrix:begin */}
 | OS | Container runtime | Status | Notes |
 |----|-------------------|--------|-------|
-| DGX OS (Spark) | Docker | Tested | Use the standard installer and `$$nemoclaw onboard`. The automatic two-DGX Spark managed-vLLM profile is Experimental, and physical two-node end-to-end validation is pending. For the profile requirements and controls, see [Set Up vLLM on Two DGX Sparks](../inference/local-inference/set-up-vllm-on-two-dgx-sparks). For the validated single-DGX Spark walkthrough with local inference, see the [NVIDIA Spark playbook](https://build.nvidia.com/spark/nemoclaw). |
+| DGX OS (Spark) | Docker | Tested | Use the standard installer and `$$nemoclaw onboard`. DGX Spark Express keeps automatic managed-vLLM serving-profile selection as option 1 and offers the fixed single-host catalog profile as option 2. The automatic two-DGX Spark managed-vLLM profile is Experimental, and physical two-node end-to-end validation is pending. For the profile requirements and controls, see [Set Up vLLM on Two DGX Sparks](../inference/local-inference/set-up-vllm-on-two-dgx-sparks). For the validated single-DGX Spark walkthrough with local inference, see the [NVIDIA Spark playbook](https://build.nvidia.com/spark/nemoclaw). |
 | DGX OS (Station) | Docker | Tested with limitations | Tested with limitations across qualified profiles on one physical DGX Station GB300; see [Additional Setup for DGX Station](additional-setup/dgx-station-preparation) for accepted profiles, the pending no-OTA DGX OS `7.6.x` end-to-end qualification, runtime gates, and current dual-Station and dedicated CI limitations. |
 | Linux | Docker | Tested | Primary tested path. Ubuntu 24.04 has host-level onboarding validation. A digest-pinned Ubuntu 26.04 userspace lane builds the CLI and runs preflight, installer, and platform contracts on eligible main pushes; Docker-host, AppArmor, Landlock, and live onboarding validation on 26.04 remain pending. Other distros (Ubuntu 22.04, Fedora, Rocky, Alma, NixOS, Arch) may work but are not validated. |
 | macOS (Apple Silicon) | Colima, Docker Desktop | Tested with limitations | Start the container runtime (Colima or Docker Desktop) before running the installer. When Homebrew is available, OpenShell uses its official formula and the gateway appears in `brew services list` as `openshell`; without Homebrew, NemoClaw uses the standalone OpenShell install and detached gateway fallback. Homebrew Colima users must install both Colima and the Docker CLI (`brew install colima docker`) before `docker info` can work. Xcode Command Line Tools (`xcode-select --install`) are typically required for Node native modules during install. NemoClaw recommends them but does not enforce them during preflight. |

diff --git a/docs/inference/choose-local-inference-server.mdx b/docs/inference/choose-local-inference-server.mdx
@@ -23,7 +23,7 @@ OpenShell intercepts that traffic and forwards it to the local endpoint configur
 | Ollama | You want the default local option and want NemoClaw to install, start, or use Ollama on supported hosts. | Appears when Ollama is installed or running, and the wizard can offer installation on supported hosts. | Ollama through the managed local route. |
 | Existing vLLM | You already run vLLM on `localhost:8000`. | Appears when NemoClaw detects the server. | `/v1/chat/completions`. |
 | Managed vLLM | You want NemoClaw to pull an image, download model weights, and manage the server container. | Appears by default on DGX Spark and DGX Station, while generic Linux NVIDIA GPU hosts require `NEMOCLAW_EXPERIMENTAL=1` or `NEMOCLAW_PROVIDER=install-vllm`. | `/v1/chat/completions`. |
-| Fixed vLLM profile | You need the fixed catalog-selected vLLM model and serving configuration. | Requires the dedicated installer flag on DGX Spark and does not appear in the provider menu. | `/v1/chat/completions`. |
+| Fixed vLLM profile | You need the fixed catalog-selected vLLM model and serving configuration. | Appears as option 2 in DGX Spark Express. Direct installation can use the dedicated installer flag. The profile does not appear in the provider menu. | `/v1/chat/completions`. |
 | Managed llama.cpp | You want NemoClaw to acquire a verified GGUF file and manage an authenticated llama.cpp container. | Experimental. Appears on a qualified DGX Spark host and supports explicit non-interactive selection. | `/v1/chat/completions`. |
 | NVIDIA NIM | You want NemoClaw to pull and manage a validated NIM container on a NIM-capable NVIDIA GPU. | Experimental and requires `NEMOCLAW_EXPERIMENTAL=1`. | `/v1/chat/completions`. |
 </AgentOnly>
@@ -33,7 +33,7 @@ OpenShell intercepts that traffic and forwards it to the local endpoint configur
 |---|---|---|---|
 | Existing vLLM | You already run vLLM on `localhost:8000`. | Appears when NemoClaw detects the server. | `/v1/chat/completions`. |
 | Managed vLLM | You want NemoClaw to pull an image, download model weights, and manage the server container. | Appears by default on DGX Spark and DGX Station, while generic Linux NVIDIA GPU hosts require `NEMOCLAW_EXPERIMENTAL=1` or `NEMOCLAW_PROVIDER=install-vllm`. | `/v1/chat/completions`. |
-| Fixed vLLM profile | You need the fixed catalog-selected vLLM model and serving configuration. | Requires the dedicated installer flag on DGX Spark and does not appear in the provider menu. | `/v1/chat/completions`. |
+| Fixed vLLM profile | You need the fixed catalog-selected vLLM model and serving configuration. | Appears as option 2 in DGX Spark Express. Direct installation can use the dedicated installer flag. The profile does not appear in the provider menu. | `/v1/chat/completions`. |
 | Managed llama.cpp | You want NemoClaw to acquire a verified GGUF file and manage an authenticated llama.cpp container. | Experimental. Appears on a qualified DGX Spark host and supports explicit non-interactive selection. | `/v1/chat/completions`. |
 | NVIDIA NIM | You want NemoClaw to pull and manage a validated NIM container on a NIM-capable NVIDIA GPU. | Experimental and requires `NEMOCLAW_EXPERIMENTAL=1`. | `/v1/chat/completions`. |
 </AgentOnly>
@@ -67,6 +67,7 @@ Refer to [Set Up vLLM](set-up-vllm).
 
 Use this feature-gated path to install the fixed catalog-selected vLLM model and runtime combination.
 The installer does not accept a provider or model override for this profile.
+DGX Spark Express offers this path as option 2 after the existing automatic managed-vLLM option.
 
 Before you start, confirm these prerequisites:
 
@@ -102,6 +103,7 @@ curl -fsSL https://www.nvidia.com/nemoclaw.sh | \
 ```
 
 The flag enables the dedicated vLLM profile gate, disables Express selection, and selects the matching catalog recipe.
+Selecting Express option 2 enables the same profile gate and selects the vLLM runtime.
 Do not combine this path with `NEMOCLAW_PROVIDER` or `NEMOCLAW_MODEL`.
 The profile rejects `NEMOCLAW_VLLM_MODEL`, `NEMOCLAW_VLLM_PORT`, and `NEMOCLAW_VLLM_EXTRA_ARGS_JSON` before installation.
 

diff --git a/docs/inference/set-up-vllm-on-two-dgx-sparks.mdx b/docs/inference/set-up-vllm-on-two-dgx-sparks.mdx
@@ -20,8 +20,9 @@ Use it only for evaluation until the required physical validation is complete.
 
 ## Understand Profile Selection
 
-DGX Spark Express attempts automatic profile selection only after it selects the managed vLLM provider.
-A provider other than `install-vllm`, an existing local inference route, `NEMOCLAW_VLLM_MODEL`, or `NEMOCLAW_VLLM_EXTRA_ARGS_JSON` remains authoritative.
+DGX Spark Express attempts automatic profile selection only after you keep option 1, the default managed-vLLM path.
+Option 2 selects the fixed single-host catalog profile and does not attempt distributed selection.
+A provider other than `install-vllm`, an existing local inference route, `NEMOCLAW_MODEL`, `NEMOCLAW_VLLM_MODEL`, or `NEMOCLAW_VLLM_EXTRA_ARGS_JSON` remains authoritative.
 Without explicit inference intent, the detector derives one exact counterpart from each qualified private `/30` rail.
 It does not scan a subnet, add SSH host keys, add authorized keys, or change SSH configuration.
 
@@ -133,7 +134,7 @@ curl -fsSL https://www.nvidia.com/nemoclaw.sh | \
   bash
 ```
 
-Accept the usage notice and the **Run express install with these settings?** prompt.
+Keep option 1, **Managed vLLM with automatic serving-profile selection**, then accept the **Run express install with these settings?** prompt.
 DGX Spark Express prints the selected topology, immutable image, pinned model revision, cache paths, and worker-first launch order before image, model, or container mutation.
 
 For optional authenticated model downloads, follow [Authenticate Hugging Face Downloads](set-up-vllm#authenticate-hugging-face-downloads) before you start the installer.

diff --git a/docs/inference/set-up-vllm.mdx b/docs/inference/set-up-vllm.mdx
@@ -257,8 +257,13 @@ On DGX Station, accepting the installer express prompt selects `NEMOCLAW_VLLM_MO
 Express uses the single-Station Ultra recipe unless a trusted reciprocal pair qualifies for distributed serving.
 Refer to [Set Up vLLM on Two DGX Stations](set-up-vllm-on-two-dgx-stations) for pair qualification, lifecycle receipts, runtime topology, and network controls.
 
-On DGX Spark, Express selects the pinned two-node profile when exactly one pretrusted reciprocal pair qualifies and no inference intent or related runtime conflicts.
-Refer to [Set Up vLLM on Two DGX Sparks](set-up-vllm-on-two-dgx-sparks) for automatic and explicit selection, profile requirements, and cleanup behavior.
+On DGX Spark, Express keeps automatic managed-vLLM serving-profile selection as option 1, the default.
+It offers the fixed local vLLM profile as option 2.
+When you select option 2, the serving catalog supplies the pinned model, runtime image, port, and serve arguments.
+The installer rejects provider and model overrides for that fixed profile, and the dedicated onboarder rejects vLLM model, port, and serve-argument overrides before it starts the managed container.
+Explicit `NEMOCLAW_MODEL` or `NEMOCLAW_VLLM_MODEL` intent retains the customizable managed-vLLM path and skips the fixed-profile choice.
+Refer to [Choose a Local Inference Server](choose-local-inference-server#install-a-fixed-local-model-profile) for fixed-profile installation and verification.
+Refer to [Set Up vLLM on Two DGX Sparks](set-up-vllm-on-two-dgx-sparks) for automatic and explicit distributed-profile selection, profile requirements, and cleanup behavior.
 
 To select the existing `deepseek-v4-flash` recipe while retaining the same one-confirmation express flow, run:
 

diff --git a/docs/reference/platform-support.mdx b/docs/reference/platform-support.mdx
@@ -78,7 +78,7 @@ For install requirements and the shorter setup-oriented platform view, refer to
 {/* platform-matrix-full:begin */}
 | OS | Container runtime | Status | PRD priority | CI | Notes |
 |----|-------------------|--------|--------------|----|-------|
-| DGX OS (Spark) | Docker | Tested | P1 | Yes | Use the standard installer and `$$nemoclaw onboard`. The automatic two-DGX Spark managed-vLLM profile is Experimental, and physical two-node end-to-end validation is pending. For the profile requirements and controls, see [Set Up vLLM on Two DGX Sparks](../inference/local-inference/set-up-vllm-on-two-dgx-sparks). For the validated single-DGX Spark walkthrough with local inference, see the [NVIDIA Spark playbook](https://build.nvidia.com/spark/nemoclaw). |
+| DGX OS (Spark) | Docker | Tested | P1 | Yes | Use the standard installer and `$$nemoclaw onboard`. DGX Spark Express keeps automatic managed-vLLM serving-profile selection as option 1 and offers the fixed single-host catalog profile as option 2. The automatic two-DGX Spark managed-vLLM profile is Experimental, and physical two-node end-to-end validation is pending. For the profile requirements and controls, see [Set Up vLLM on Two DGX Sparks](../inference/local-inference/set-up-vllm-on-two-dgx-sparks). For the validated single-DGX Spark walkthrough with local inference, see the [NVIDIA Spark playbook](https://build.nvidia.com/spark/nemoclaw). |
 | DGX OS (Station) | Docker | Tested with limitations | P1 | No | The PRD marks this platform as P1. Physical validation on one DGX Station GB300 covers generic Ubuntu 24.04 ARM64, stock DGX OS `7.5.0`, the April 2026 NVIDIA Colossus BaseOS profile, and the June 2026 NVIDIA AI Developer Tools profile. A physical no-OTA DGX OS `7.6.0` host provided the release and hardware profile used for its stable workstation-family classifier and passed read-only eligibility and runtime-command preflight. Full Station Express end-to-end qualification for the accepted no-OTA DGX OS `7.6.x` profile is pending. The profile remains subject to the same physical GB300, driver, ECC, Docker, CDI, and container GPU validation. Clean-host end-to-end validation passed on generic Ubuntu and Colossus BaseOS; stock DGX OS and AI Developer Tools completed Station Express validation. The DGX OS `7.5.0` run used released OpenShell `0.0.85`, local Nemotron Ultra serving, sandbox `cuInit(0)`, and a Hermes write/read file-tool task. A dual-Station configuration has not been validated, and dedicated CI coverage is not available. Direct-GPU policies expose only the exact read-only BDF directory for each discovered display-class PCI device with NVIDIA vendor ID (`0x10de`) and GB300 device ID (`0x31c2` or `0x31c3`) plus required existing topology and module paths; they do not expose `/sys`, the PCI parent subtree, or sysfs write access. During physical validation, reads of `/sys/fs/cgroup/cgroup.controllers` and `/sys/class/net/lo/address` remained denied. For canonical hardware qualification, image requirements, preparation, repair limits, reboot handoff, and the explicit temporary metadata override, see [Prepare DGX Station to Install NemoClaw](../get-started/additional-setup/dgx-station-preparation). |
 | Linux | Docker | Tested | P0 | Yes | Primary tested path. Ubuntu 24.04 has host-level onboarding validation. A digest-pinned Ubuntu 26.04 userspace lane builds the CLI and runs preflight, installer, and platform contracts on eligible main pushes; Docker-host, AppArmor, Landlock, and live onboarding validation on 26.04 remain pending. Other distros (Ubuntu 22.04, Fedora, Rocky, Alma, NixOS, Arch) may work but are not validated. |
 | macOS (Apple Silicon) | Colima, Docker Desktop | Tested with limitations | P0 | Yes | Start the container runtime (Colima or Docker Desktop) before running the installer. When Homebrew is available, OpenShell uses its official formula and the gateway appears in `brew services list` as `openshell`; without Homebrew, NemoClaw uses the standalone OpenShell install and detached gateway fallback. Homebrew Colima users must install both Colima and the Docker CLI (`brew install colima docker`) before `docker info` can work. Xcode Command Line Tools (`xcode-select --install`) are typically required for Node native modules during install. NemoClaw recommends them but does not enforce them during preflight. |

diff --git a/docs/resources/prompt-assets/dgx-spark.md b/docs/resources/prompt-assets/dgx-spark.md
@@ -7,17 +7,33 @@
 
 Use these instructions only after hardware detection confirms DGX Spark.
 
-Explain that Express keeps the selected agent, uses local vLLM with the default Qwen model, leaves optional setup at its defaults, and downloads the vLLM container and model.
-Include the third-party-software notice, then ask: "Run Express install with these settings?"
+Explain that Express keeps the selected agent, leaves optional setup at its defaults, and offers two DGX Spark inference setups.
+Inference choices:
+
+1. Managed vLLM with automatic serving-profile selection. This is the default and preserves the current Express behavior.
+2. `nvidia/Qwen3.6-35B-A3B-NVFP4` with the fixed catalog-backed vLLM profile.
+
+Include the third-party-software notice after the user chooses, then ask: "Run Express install with these settings?"
 Choices:
 
-1. Yes, use the DGX Spark Express defaults.
-2. No, let me choose the runtime and model.
+1. Yes, use the selected DGX Spark inference setup.
+2. No, continue with the normal provider selection.
 
-If Express is selected:
+For option 1:
 
 - Set `NEMOCLAW_PROVIDER=install-vllm`.
-- Leave `NEMOCLAW_VLLM_MODEL` and `NEMOCLAW_MODEL` unset so the installed release selects its DGX Spark default, currently `nvidia/Qwen3.6-35B-A3B-NVFP4`.
+- Leave `NEMOCLAW_ENABLE_LOCAL_MODEL_PROFILE`, `NEMOCLAW_LOCAL_MODEL_RUNTIME`, `NEMOCLAW_MODEL`, and `NEMOCLAW_VLLM_MODEL` unset.
+- Explain that the installed release performs automatic DGX Spark serving-profile selection.
+
+For option 2:
+
+- Set `NEMOCLAW_ENABLE_LOCAL_MODEL_PROFILE=1` and `NEMOCLAW_LOCAL_MODEL_RUNTIME=vllm`.
+- Leave `NEMOCLAW_PROVIDER`, `NEMOCLAW_MODEL`, `NEMOCLAW_VLLM_MODEL`, `NEMOCLAW_VLLM_PORT`, and `NEMOCLAW_VLLM_EXTRA_ARGS_JSON` unset.
+- Explain that the serving catalog selects the fixed model, runtime image, port, and vLLM arguments.
+- Explain that the fixed profile serves `nvidia/Qwen3.6-35B-A3B-NVFP4`.
+
+For either accepted Express option:
+
 - Set `NEMOCLAW_AGENT` to the agent already selected in the starter prompt.
 - Set `NEMOCLAW_NON_INTERACTIVE=1`, `NEMOCLAW_NON_INTERACTIVE_SUDO_MODE=prompt`, `NEMOCLAW_YES=1`, and `NEMOCLAW_POLICY_MODE=suggested`.
 - Set `NEMOCLAW_ACCEPT_THIRD_PARTY_SOFTWARE=1` when Express is accepted.

diff --git a/docs/resources/starter-prompt.md b/docs/resources/starter-prompt.md
@@ -79,9 +79,9 @@ Set `NEMOCLAW_AGENT=langchain-deepagents-code` for Deep Agents, or use `nemo-dee
 
 After the readiness check, load exactly one matching instruction asset before provider selection:
 
-- Confirmed DGX Spark: [DGX Spark Express instructions](https://raw.githubusercontent.com/NVIDIA/NemoClaw/bf46e62f901825f19e570c17f8c870a0eae04fbc/docs/resources/prompt-assets/dgx-spark.md).
-- Confirmed DGX Station: [DGX Station installation instructions](https://raw.githubusercontent.com/NVIDIA/NemoClaw/bf46e62f901825f19e570c17f8c870a0eae04fbc/docs/resources/prompt-assets/dgx-station.md).
-- Officially detected Windows WSL: [Windows WSL Express instructions](https://raw.githubusercontent.com/NVIDIA/NemoClaw/bf46e62f901825f19e570c17f8c870a0eae04fbc/docs/resources/prompt-assets/windows-wsl.md).
+- Confirmed DGX Spark: [DGX Spark Express instructions](https://raw.githubusercontent.com/NVIDIA/NemoClaw/4394858b3bae38b04768619f99b9614161f1b565/docs/resources/prompt-assets/dgx-spark.md).
+- Confirmed DGX Station: [DGX Station installation instructions](https://raw.githubusercontent.com/NVIDIA/NemoClaw/4394858b3bae38b04768619f99b9614161f1b565/docs/resources/prompt-assets/dgx-station.md).
+- Officially detected Windows WSL: [Windows WSL Express instructions](https://raw.githubusercontent.com/NVIDIA/NemoClaw/4394858b3bae38b04768619f99b9614161f1b565/docs/resources/prompt-assets/windows-wsl.md).
 
 Read the matching raw Markdown file completely and follow it before continuing.
 Do not load a platform asset for any other computer.