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/docs.html

@@ -42,32 +42,29 @@
 
 <section id="models">
   <h1>The running models</h1>
-  <p>Three models serve the family, each on its own hardware. The homepage status
-  cards above show whether each one is up right now.</p>
+  <p>Three models serve the family. The homepage status cards show whether
+  each one is up right now.</p>
 
   <h2>frank-large — the big brain</h2>
   <ul>
-    <li><strong>Model:</strong> Qwen3.8-Flash-Next UD-IQ4_XS, served by unsloth llama.cpp with the model's own MTP draft head (depth 2).</li>
-    <li><strong>Hardware:</strong> Dankclaw's Strix Halo iGPU (gfx1151), shared with the whole host.</li>
-    <li><strong>Best for:</strong> long, thoughtful text conversations at a 200k-token window.</li>
-    <li><strong>Capacity:</strong> exactly one conversation resident at a time. A second waits — politely, but it waits.</li>
+    <li><strong>Model:</strong> Qwen3.8-Flash-Next, UD-IQ4_XS (87.3 GiB).</li>
+    <li><strong>Capacity:</strong> 200k-token context, exactly one conversation at a time. A second waits — politely, but it waits.</li>
+    <li><strong>Best for:</strong> long, thoughtful text conversations.</li>
     <li><strong>Not for:</strong> images. It cannot see them.</li>
   </ul>
 
   <h2>frank-small — the eyes</h2>
   <ul>
-    <li><strong>Model:</strong> Gemma4-12B QAT (HauhauCS Balanced, Q4_K_M) with MTP + n-gram speculative decoding.</li>
-    <li><strong>Hardware:</strong> Dankclaw's RTX 3090.</li>
-    <li><strong>Best for:</strong> anything with a picture — screenshots, photos, diagrams. Fastest decode of the fleet at long context, and the endpoint that gets most daily traffic.</li>
+    <li><strong>Model:</strong> Gemma4-12B QAT (Balanced, Q4_K_M, 7.4 GiB).</li>
     <li><strong>Capacity:</strong> one million tokens of pooled context across four simultaneous conversations (up to 262k each).</li>
+    <li><strong>Best for:</strong> anything with a picture — screenshots, photos, diagrams. Fastest decode of the fleet at long context, and the endpoint that gets most daily traffic.</li>
   </ul>
 
   <h2>frank-medium — the 27B generalist</h2>
   <ul>
-    <li><strong>Model:</strong> Qwen3.8-27B-Uncensored at FP8, on vllm-radiance with a DFlash2 draft head.</li>
-    <li><strong>Hardware:</strong> Dankserver's two Radeon R9700s as ONE tensor-parallel engine (TP=2).</li>
-    <li><strong>Best for:</strong> general chat and reasoning when the big brain is busy; the biggest pure-language model we run, and the fastest we have measured.</li>
+    <li><strong>Model:</strong> Qwen3.8-27B-Uncensored, FP8 (~31 GiB).</li>
     <li><strong>Capacity:</strong> 262k-token context shared by up to eight conversations at once. It can see pictures too; <code>frank-small</code> is the faster eye and holds four conversations.</li>
+    <li><strong>Best for:</strong> general chat and reasoning when the big brain is busy — and the only seat with eight chairs at once.</li>
   </ul>
 
   <p class="foot-note">Which one to pick? Screenshots and photos: <code>frank-small</code>.