minaiml - PYTHAI delivery layer: what runs on a laptop and a phone

README.md

@@ -1,10 +1,29 @@
 ---
-title: Minaiml
-emoji: 📈
-colorFrom: blue
-colorTo: indigo
+title: minaiml
+emoji: 📱
+colorFrom: gray
+colorTo: yellow
 sdk: static
 pinned: false
+short_description: delivery software for models on laptops and phones
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+<p><b><a href="https://github.com/minaiml" target="_blank" rel="noopener">minaiml</a></b> (say it <i>minimal</i>) is <b><a href="https://huggingface.co/PYTHAI" target="_blank" rel="noopener">PYTHAI</a></b>'s delivery layer: the software that runs reasonable-sized models on hardware you already own. A mixture-of-experts model is mostly idle — a router wakes a handful of experts per token and leaves the rest on disk. Delivery is the art of exploiting that.</p>
+
+<table>
+<tr><th align="left">device</th><th align="left">model</th><th align="left">tok/s</th><th align="left">resident</th><th align="left">engine</th></tr>
+<tr><td>MacBook Pro M3 Max, 48&nbsp;GB</td><td>Qwen3.5-397B-A17B</td><td>4.36</td><td>~6&nbsp;GB of 209&nbsp;GB</td><td><a href="https://github.com/minaiml/flash-moe" target="_blank" rel="noopener">flash-moe</a></td></tr>
+<tr><td>iPhone 17</td><td>Qwen3.5-35B-A3B</td><td>11</td><td>1.4&nbsp;GB of 13&nbsp;GB</td><td><a href="https://github.com/minaiml/Flash-iOS" target="_blank" rel="noopener">Flash-iOS</a></td></tr>
+<tr><td>Raspberry Pi 5, 8&nbsp;GB</td><td>DeepSeek-V4-Flash</td><td>&mdash;</td><td>&mdash;</td><td><a href="https://github.com/minaiml/flash-pi-dsv4" target="_blank" rel="noopener">flash-pi-dsv4</a></td></tr>
+<tr><td>2-core CPU VPS, no GPU</td><td><a href="https://huggingface.co/PYTHAI/mindXtrain39" target="_blank" rel="noopener">mindXtrain39</a>, 135M dense</td><td>0.19</td><td>&mdash;</td><td>Ollama</td></tr>
+</table>
+
+<p>The slowest row is ours, and it stays: a 135-million-parameter dense model runs three hundred times slower than a 397-billion-parameter sparse one. <b>Sparsity, not size, decides what a small machine can run.</b></p>
+
+<p><b>The catalogue lives on GitHub</b> — <a href="https://github.com/minaiml" target="_blank" rel="noopener">github.com/minaiml</a>: laptop engines, MoE streaming, phone and edge runtimes, browser targets, cluster inference, on-device speech and adaptation. Every fork carries a <code>FORK.json</code> recording upstream, the commit we pinned, the date and the licence — including the four that declare no licence upstream and are therefore never redistributed.</p>
+
+<p><b>The models are at <a href="https://huggingface.co/PYTHAI" target="_blank" rel="noopener">PYTHAI</a></b>, licence-pinned at a commit: <a href="https://huggingface.co/PYTHAI/Qwen3.8-27B-fork" target="_blank" rel="noopener">Qwen3.8</a> · <a href="https://huggingface.co/PYTHAI/GLM-5.3-Flash-fork" target="_blank" rel="noopener">GLM-5.3-Flash</a> · <a href="https://huggingface.co/PYTHAI/Kimi-K3-fork" target="_blank" rel="noopener">Kimi K3</a> · <a href="https://huggingface.co/PYTHAI/granite-4.2-8b-fork" target="_blank" rel="noopener">Granite 4.2</a>. Delivery software here, weights there.</p>
+
+<p><b>Elsewhere:</b> <a href="https://pythai.net" target="_blank" rel="noopener">pythai.net</a> · <a href="https://mindx.pythai.net" target="_blank" rel="noopener">mindx.pythai.net</a> · <a href="https://huggingface.co/spaces/PYTHAI/mindX" target="_blank" rel="noopener">mindX, live</a>. Built by <a href="https://github.com/Professor-Codephreak" target="_blank" rel="noopener">Professor Codephreak</a>.</p>
+
+<p>Intelligence doesn't require a data center. It requires knowing which parameters are awake.</p>

index.html

@@ -1,19 +1,54 @@
-<!doctype html>
-<html>
-	<head>
-		<meta charset="utf-8" />
-		<meta name="viewport" content="width=device-width" />
-		<title>My static Space</title>
-		<link rel="stylesheet" href="style.css" />
-	</head>
-	<body>
-		<div class="card">
-			<h1>Welcome to your static Space!</h1>
-			<p>You can modify this app directly by editing <i>index.html</i> in the Files and versions tab.</p>
-			<p>
-				Also don't forget to check the
-				<a href="https://huggingface.co/docs/hub/spaces" target="_blank">Spaces documentation</a>.
-			</p>
-		</div>
-	</body>
+<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="utf-8">
+<meta name="viewport" content="width=device-width, initial-scale=1">
+<title>minaiml</title>
+<meta name="description" content="minaiml — delivery software for reasonable-sized models on laptops and smartphones.">
+<base target="_blank">
+<style>
+:root { --bg:#07090a; --panel:#0e1211; --line:rgba(232,230,223,.08); --text:#e8e6df; --text2:#a3ada7; --gold:#d6b25e; }
+* { box-sizing: border-box; }
+body { margin:0; background:var(--bg); color:var(--text2); font:16px/1.65 ui-sans-serif, system-ui, -apple-system, "Segoe UI", sans-serif; }
+main { max-width: 820px; margin: 0 auto; padding: 48px 16px 64px; }
+h1 { color:var(--text); font-size:2.2rem; line-height:1.1; margin:0 0 6px; letter-spacing:-.02em; }
+.say { font: .8rem ui-monospace, Menlo, monospace; color:var(--gold); letter-spacing:.12em; text-transform:uppercase; margin:0 0 28px; }
+p { margin: 0 0 18px; }
+b { color: var(--text); font-weight: 600; }
+a { color: var(--gold); text-decoration: none; }
+a:hover { text-decoration: underline; }
+code { font: .86em ui-monospace, Menlo, monospace; }
+.scroll { overflow-x: auto; border: 1px solid var(--line); border-radius: 10px; margin: 8px 0 26px; }
+table { border-collapse: collapse; width: 100%; font-size: .92rem; }
+th, td { text-align: left; padding: 10px 14px; border-bottom: 1px solid var(--line); vertical-align: top; }
+tr:last-child td { border-bottom: 0; }
+th { font: .72rem ui-monospace, Menlo, monospace; letter-spacing: .12em; text-transform: uppercase; color: #6d7771; background: var(--panel); }
+td:first-child { white-space: nowrap; }
+</style>
+</head>
+<body>
+<main>
+<h1>minaiml</h1>
+<p class="say">min ai ml — models on hardware you own</p>
+<p><b><a href="https://github.com/minaiml" target="_blank" rel="noopener">minaiml</a></b> (say it <i>minimal</i>) is <b><a href="https://huggingface.co/PYTHAI" target="_blank" rel="noopener">PYTHAI</a></b>'s delivery layer: the software that runs reasonable-sized models on hardware you already own. A mixture-of-experts model is mostly idle — a router wakes a handful of experts per token and leaves the rest on disk. Delivery is the art of exploiting that.</p>
+
+<div class="scroll"><table>
+<tr><th align="left">device</th><th align="left">model</th><th align="left">tok/s</th><th align="left">resident</th><th align="left">engine</th></tr>
+<tr><td>MacBook Pro M3 Max, 48&nbsp;GB</td><td>Qwen3.5-397B-A17B</td><td>4.36</td><td>~6&nbsp;GB of 209&nbsp;GB</td><td><a href="https://github.com/minaiml/flash-moe" target="_blank" rel="noopener">flash-moe</a></td></tr>
+<tr><td>iPhone 17</td><td>Qwen3.5-35B-A3B</td><td>11</td><td>1.4&nbsp;GB of 13&nbsp;GB</td><td><a href="https://github.com/minaiml/Flash-iOS" target="_blank" rel="noopener">Flash-iOS</a></td></tr>
+<tr><td>Raspberry Pi 5, 8&nbsp;GB</td><td>DeepSeek-V4-Flash</td><td>&mdash;</td><td>&mdash;</td><td><a href="https://github.com/minaiml/flash-pi-dsv4" target="_blank" rel="noopener">flash-pi-dsv4</a></td></tr>
+<tr><td>2-core CPU VPS, no GPU</td><td><a href="https://huggingface.co/PYTHAI/mindXtrain39" target="_blank" rel="noopener">mindXtrain39</a>, 135M dense</td><td>0.19</td><td>&mdash;</td><td>Ollama</td></tr>
+</table></div>
+
+<p>The slowest row is ours, and it stays: a 135-million-parameter dense model runs three hundred times slower than a 397-billion-parameter sparse one. <b>Sparsity, not size, decides what a small machine can run.</b></p>
+
+<p><b>The catalogue lives on GitHub</b> — <a href="https://github.com/minaiml" target="_blank" rel="noopener">github.com/minaiml</a>: laptop engines, MoE streaming, phone and edge runtimes, browser targets, cluster inference, on-device speech and adaptation. Every fork carries a <code>FORK.json</code> recording upstream, the commit we pinned, the date and the licence — including the four that declare no licence upstream and are therefore never redistributed.</p>
+
+<p><b>The models are at <a href="https://huggingface.co/PYTHAI" target="_blank" rel="noopener">PYTHAI</a></b>, licence-pinned at a commit: <a href="https://huggingface.co/PYTHAI/Qwen3.8-27B-fork" target="_blank" rel="noopener">Qwen3.8</a> · <a href="https://huggingface.co/PYTHAI/GLM-5.3-Flash-fork" target="_blank" rel="noopener">GLM-5.3-Flash</a> · <a href="https://huggingface.co/PYTHAI/Kimi-K3-fork" target="_blank" rel="noopener">Kimi K3</a> · <a href="https://huggingface.co/PYTHAI/granite-4.2-8b-fork" target="_blank" rel="noopener">Granite 4.2</a>. Delivery software here, weights there.</p>
+
+<p><b>Elsewhere:</b> <a href="https://pythai.net" target="_blank" rel="noopener">pythai.net</a> · <a href="https://mindx.pythai.net" target="_blank" rel="noopener">mindx.pythai.net</a> · <a href="https://huggingface.co/spaces/PYTHAI/mindX" target="_blank" rel="noopener">mindX, live</a>. Built by <a href="https://github.com/Professor-Codephreak" target="_blank" rel="noopener">Professor Codephreak</a>.</p>
+
+<p>Intelligence doesn't require a data center. It requires knowing which parameters are awake.</p>
+</main>
+</body>
 </html>