homepage: AI section to the bottom; model-only AI descriptions

The user page now orders Web Apps, Media Library Apps, AI — the models sit
at the bottom, below the apps people click. The AI card and /docs#models
descriptions drop the infrastructure (runtimes, GPUs, tensor parallelism,
draft heads) in favor of what users care about: the hosted model, its
size, the context/parallel capacity, and what it's good at.

shared/homepage/services.json

@@ -255,7 +255,7 @@
     "name": "frank-large",
     "category": "user",
     "section": "AI",
-    "description": "The big brain. Qwen3.8-Flash-Next UD-IQ4_XS on unsloth llama.cpp, running on Dankclaw's Strix Halo iGPU. Text-only; one conversation resident at a time.",
+    "description": "Qwen3.8-Flash-Next (UD-IQ4_XS, 87.3 GiB) — 200k-token context, one conversation at a time. The big brain: long, thoughtful text conversations. Text only; it cannot see images.",
     "url": "",
     "docs": "/docs#models",
     "probe": "127.0.0.1:7770",
@@ -267,7 +267,7 @@
     "name": "frank-medium",
     "category": "user",
     "section": "AI",
-    "description": "The 27B generalist. Qwen3.8-27B-Uncensored at FP8 on vllm-radiance, one tensor-parallel process across Dankserver's two R9700s with a DFlash2 drafter; 262k-token context shared by up to eight conversations.",
+    "description": "Qwen3.8-27B-Uncensored (FP8, ~31 GiB) — 262k-token context shared by up to eight conversations. The generalist: chat and reasoning, and it sees images.",
     "url": "",
     "docs": "/docs#models",
     "probe": "192.168.0.235:7770",
@@ -279,7 +279,7 @@
     "name": "frank-small",
     "category": "user",
     "section": "AI",
-    "description": "The vision path. HauhauCS Gemma4-12B QAT (Balanced, Q4_K_M) with MTP + ngram spec-decode on Dankclaw's RTX 3090. Sees images; 1M-token pool across four conversations.",
+    "description": "Gemma4-12B QAT (Q4_K_M, 7.4 GiB) — 1M-token pool across four 262k-token conversations. The eyes: screenshots, photos, diagrams; the fastest of the three.",
     "url": "",
     "docs": "/docs#models",
     "probe": "127.0.0.1:7771",