refresh hub data: ornith + titus rows

[agent:cc] org-card: chart is single-stream only - filter out concurrency>1 rows (no conc-aggregate mixing)

[agent:cc] org-card: null borrowed prefill/power on conc=4 rows

[agent:cc] org-card: refine concurrent-row notes (adversarial review)

[agent:cc] org-card: 35B-A3B vLLM-NVFP4-EP vs llama.cpp-Q4 concurrency rows (2026-06-22)

refresh: current model roster - 103 rows / 21 models from llm-lab card-bench 2026-06-21 (adds Qwen3.6-27B quant ladder + 35B sweep + candidates; smoke/trial excluded)

Update Gradio SDK pin

Add RLM long-context note

Remove Recommended all-rounder pick (consistency with lab dashboard); keep factual fastest/biggest/efficient category picks

v7: picks-only public surface + recommended all-rounder (production model, public metrics only) + held-at-rated-power telemetry note

Add public budget-decision views: speed-vs-VRAM scatter w/ budget filter + picks + telemetry note (v4/v5 hub; speed/power/VRAM only, desktop variant)

Add public budget-decision views: speed-vs-VRAM scatter w/ budget filter + picks + telemetry note (v4/v5 hub; speed/power/VRAM only, desktop variant)

Add public budget-decision views: speed-vs-VRAM scatter w/ budget filter + picks + telemetry note (v4/v5 hub; speed/power/VRAM only, desktop variant)

Use Gradio org-card Space config

Set static Space SDK version

Fix org card Space configuration

Publish RTX PRO 4000 org card

Remove internal tagline from footer

Fix colorFrom: cyan is not in HF allowed set, use blue/indigo

Add static landing page with GPU specs and community resources

initial commit