What this app does

Public model arenas optimise for crowdsourced vote volume on cloud APIs and never know what hardware their votes ran on. Orionfold Arena is the operator-driven, local-first alternative: a one-process cockpit that drives every quant, LoRA, bench, harness, and skill your Spark has produced — private eval leaderboards, a cost-per-quality efficiency frontier, side-by-side rubric-scored compare, live telemetry, and a co-iteration Lab. Your prompts, telemetry, and eval data never leave the box.

What you can do with it

Chat against the resident brain with live tok/s + unified-memory telemetry
Side-by-side rubric-scored compare (resident lane vs OpenRouter frontier)
Private leaderboards + a cost/quality Pareto frontier anchored to real Spark hardware
Browse the model/notebook/bench/harness catalog with quant economics
A Lab board for the operator+AI build loop, with a private notes margin

Audience — DGX Spark operators (GB10, 128 GB unified memory) and edge-AI builders who want a beautiful, local-first cockpit over their own artifacts — no hosted SaaS, no data egress.

Interactive preview Open the live demo → Recorded on a DGX Spark, replayed in your browser — no sidecar needed. The story Read the launch → What it took to build, with mined metrics and a full feature tour.

Known drift

Disclosed limitations with explicit bounds — the scope is named, not implied.

Live surfaces (chat, compare, telemetry, Lab notes) need the local sidecar: On the public web preview the sidecar is offline by design; ~5 surfaces degrade to their static mirror data + an offline banner. The leaderboard, models browser, frontier, and Lab board render fully static.