// Posts tagged: nvidia

Getting DeepSeek V4 Flash with Vision Running on the Dual Spark Cluster

2026.09.16·9 min read

The dual DGX Spark cluster moved from a conservative DeepSeek V4 text endpoint to DeepSeek V4 Flash Vision-Exp after wrong turns through oversized models, generic runtimes, missing encoders, and RDMA failures.

homelab ai llm nvidia debugging building-in-public

Adding A Dual-Node NVIDIA Spark Cluster for Real Local AI in the Homelab

2026.09.15·9 min read

A dual-node NVIDIA Spark cluster runs DeepSeek V4 Flash locally, extending the homelab from one RTX 5090 workstation toward a higher-fidelity local AI inference tier.

homelab ai llm nvidia how-to building-in-public