Description
Description
The onboard wizard Ollama starter model list shows only qwen2.5:7b and nemotron-3-nano:30b. Qwen3.6 35B — the COMPUTEX POR default model for DGX Spark — is not listed. Users can only reach it via "Other..." manual entry, which breaks the express setup auto-select design. The express setup flow cannot auto-pull the POR default model without this being added to the starter list.
Environment
Device: DGX Spark (spark-dadc, 10.173.104.110)
OS: DGX Spark FastOS 1.135.29 (2026-04-13, customer build)
Architecture: aarch64
Node.js: v22.22.2
npm: 10.9.7
Docker: Docker 29.2.1
OpenShell CLI: openshell 0.0.36
NemoClaw: v0.0.37
OpenClaw: N/A (onboard not completed)
Ollama: 0.23.2
Steps to Reproduce
1. Run: nemoclaw onboard on DGX Spark
2. Select provider: Local Ollama
3. Observe the starter model list
Expected Result
Starter model list includes Qwen3.6 35B as the default/recommended option for DGX Spark,
per COMPUTEX POR: "Default model at COMPUTEX: Qwen3.6 35B"
Actual Result
Ollama starter models:
1) qwen2.5:7b
2) nemotron-3-nano:30b
3) Other...
Qwen3.6 35B is not listed. User must select "Other..." and manually type the model name.
Logs
Not captured — visible in onboard wizard stdout above.
Bug Details
| Field |
Value |
| Priority |
Unprioritized |
| Action |
Dev - Open - To fix |
| Disposition |
Open issue |
| Module |
Machine Learning - NemoClaw |
| Keyword |
DGX_Spark_OTA_Computex, NemoClaw, NEMOCLAW_GH_SYNC_APPROVAL, NemoClaw_Inference, NemoClaw_Onboard |
[NVB#6157917]
Description
Description
Environment Steps to Reproduce Expected Result Actual ResultOllama starter models: 1) qwen2.5:7b 2) nemotron-3-nano:30b 3) Other... Qwen3.6 35B is not listed. User must select "Other..." and manually type the model name.LogsBug Details
[NVB#6157917]