Attributed 2026-10-01 13:51:36 CDT. Dual Sparks had coder-flash / coder / vision loaded — Qwen3.8-Flash-Next NVFP4, 262144 context, TP2 across both GB10 boxes. About 63 GiB GPU memory per Spark worker (~50% of a ~124.6 GiB unified pool). GPU util sat around 92–96% from that residency.
Live generation was idle (0 tok/s) on every node. That is the only live throughput number from this pull. A later coordinator-page pull showed live gauges as connecting / incomplete, so this idle probe remains the published snapshot. No invented tok/s.
Catalog figures such as ~80–82 tok/s for agent / lightning, ~65 for agent-gemma, and ~60 for omni are dated roster copy; the Oct 1 probe saw agent unloaded. The coordinator roster (Capabilities) lists resident agent / lightning, embed, and Kokoro tts, with on-demand Mage-Flow image, omni, ocr, translate, stt, agent-gemma, tts-clone, and coder-ornith.
OCR, translate, STT, and TTS selectors were unloaded in the Oct 1 window. The Gaming PC (RTX 5090) peer was online and is the exclusive media box (music, video, image edit) — not the Spark chat worker. Mac Studio M5 Max had embeddings ready; its GPU block from that pull was mis-templated and is not published.
No private hostnames, no live charts, no public gateway URL, no connect recipes.