Hybrid datacenter, storage & backup — notes from work, homelab and life.
While deploying HPE Morpheus Manager from Windows, the installer reported: Connection failed: SECURITY WARNING: Host key for 192.0.2.50:22 has changed! This … Read more
I’ve been evaluating DFlash2 speculative decoding for Qwen3.8-27B (NVFP4) on a single NVIDIA DGX Spark (GB10) in the homelab — the successor to the Qwen3.6-27B … Read more
Before switching to DFlash2, I ran Qwen3.8-27B (NVFP4) on vLLM 0.27.2rc1 with MTP speculative decoding (3 tokens) on the DGX Spark (GB10). This is the baseline … Read more
Before Qwen3.8 landed, Qwen3.6-27B (NVFP4) with DFlash speculative decoding was my favourite local model on the DGX Spark (GB10) — the dense 27B quality I … Read more
A small, fast model — Qwen2.5-3B (65k context) — served through Ollama, benchmarked to decide whether it was worth moving to llama.cpp. Metric Median Output … Read more
Qwen3.6-27B-FP8, a dense 27B model on the DGX Spark (GB10) — every token activates all 27B parameters, so it trades speed for per-token quality. Metric Value … Read more
Qwen3-VL-8B-FP8, the vision model, filling the fast auxiliary roles on the DGX Spark (GB10) — titles, approvals, MCP routing, screenshot follow-ups. Metric … Read more
Running NVIDIA Nemotron-3 Super 120B (A12B, NVFP4) — a Mixture-of-Experts model with ~12B active parameters per token — on a single DGX Spark (GB10). Snapshot … Read more
In 2025, Karl Dag Gursli, Håvar Eggereide and I sat down to plan what we should organise for TC26. With all the rapid changes in the IT landscape, we concluded … Read more