Spaces:
Running
Running
FreeCPU: ~6-7 tok/s
Browse files- index.html +269 -269
index.html
CHANGED
|
@@ -1,269 +1,269 @@
|
|
| 1 |
-
<!doctype html>
|
| 2 |
-
<html lang="en">
|
| 3 |
-
<head>
|
| 4 |
-
<meta charset="utf-8">
|
| 5 |
-
<meta name="viewport" content="width=device-width, initial-scale=1">
|
| 6 |
-
<title>VKUE — VIDRAFT Kernel Ubiquitous Engine</title>
|
| 7 |
-
<meta name="description" content="VKUE Efficiency Leaderboard — serve frontier-class models on minimal hardware.">
|
| 8 |
-
</head>
|
| 9 |
-
<body>
|
| 10 |
-
<style>
|
| 11 |
-
:root{
|
| 12 |
-
--ground:#F4F7F7; --panel:#FFFFFF; --ink:#0B1418; --muted:#5B6B70;
|
| 13 |
-
--line:#D7E0E1; --accent:#0E8C9E; --accent-soft:#E2F4F6; --hero:#B0791A;
|
| 14 |
-
--hero-soft:#FBF1DE; --good:#1F8A5B; --good-soft:#E4F3EC; --star:#0E8C9E;
|
| 15 |
-
--mono:ui-monospace,"SFMono-Regular","Cascadia Code","Consolas",monospace;
|
| 16 |
-
--sans:-apple-system,BlinkMacSystemFont,"Segoe UI","Apple SD Gothic Neo","Malgun Gothic",Roboto,sans-serif;
|
| 17 |
-
}
|
| 18 |
-
@media (prefers-color-scheme:dark){
|
| 19 |
-
:root{
|
| 20 |
-
--ground:#0B1418; --panel:#111E23; --ink:#E6EFF0; --muted:#8CA1A6;
|
| 21 |
-
--line:#22343A; --accent:#22B8CF; --accent-soft:#0F2A31; --hero:#E0A83E;
|
| 22 |
-
--hero-soft:#2A2113; --good:#43D08A; --good-soft:#10281D; --star:#22B8CF;
|
| 23 |
-
}
|
| 24 |
-
}
|
| 25 |
-
:root[data-theme="light"]{
|
| 26 |
-
--ground:#F4F7F7; --panel:#FFFFFF; --ink:#0B1418; --muted:#5B6B70;
|
| 27 |
-
--line:#D7E0E1; --accent:#0E8C9E; --accent-soft:#E2F4F6; --hero:#B0791A;
|
| 28 |
-
--hero-soft:#FBF1DE; --good:#1F8A5B; --good-soft:#E4F3EC; --star:#0E8C9E;
|
| 29 |
-
}
|
| 30 |
-
:root[data-theme="dark"]{
|
| 31 |
-
--ground:#0B1418; --panel:#111E23; --ink:#E6EFF0; --muted:#8CA1A6;
|
| 32 |
-
--line:#22343A; --accent:#22B8CF; --accent-soft:#0F2A31; --hero:#E0A83E;
|
| 33 |
-
--hero-soft:#2A2113; --good:#43D08A; --good-soft:#10281D; --star:#22B8CF;
|
| 34 |
-
}
|
| 35 |
-
*{box-sizing:border-box}
|
| 36 |
-
body{margin:0;background:var(--ground);color:var(--ink);font-family:var(--sans);
|
| 37 |
-
line-height:1.5;-webkit-font-smoothing:antialiased}
|
| 38 |
-
.wrap{max-width:1060px;margin:0 auto;padding:clamp(20px,4vw,52px) clamp(16px,4vw,40px)}
|
| 39 |
-
.eyebrow{font-family:var(--mono);font-size:12px;letter-spacing:.22em;text-transform:uppercase;
|
| 40 |
-
color:var(--accent);margin:0 0 14px}
|
| 41 |
-
.wordmark{font-family:var(--mono);font-weight:700;font-size:clamp(38px,8vw,68px);
|
| 42 |
-
letter-spacing:-.01em;margin:0;line-height:.98;text-wrap:balance}
|
| 43 |
-
.wordmark small{color:var(--muted);font-weight:400;font-size:.30em;letter-spacing:.02em;display:block;margin-top:12px}
|
| 44 |
-
.tagline{font-size:clamp(17px,2.4vw,22px);color:var(--ink);margin:18px 0 0;max-width:52ch;text-wrap:balance}
|
| 45 |
-
.tagline b{color:var(--accent)}
|
| 46 |
-
.sibs{display:flex;flex-wrap:wrap;gap:10px;margin-top:22px}
|
| 47 |
-
.chip{font-family:var(--mono);font-size:12.5px;padding:7px 13px;border:1px solid var(--line);
|
| 48 |
-
border-radius:999px;color:var(--muted);background:var(--panel)}
|
| 49 |
-
.chip b{color:var(--ink)}
|
| 50 |
-
.chip.now{border-color:var(--accent);color:var(--accent)}
|
| 51 |
-
.chip.link{text-decoration:none;cursor:pointer;transition:border-color .15s,color .15s}
|
| 52 |
-
.chip.link:hover{border-color:var(--accent);color:var(--accent)}
|
| 53 |
-
.card a.tlink{text-decoration:none}
|
| 54 |
-
.card a.tlink:hover{text-decoration:underline}
|
| 55 |
-
|
| 56 |
-
.stats{display:grid;grid-template-columns:repeat(auto-fit,minmax(198px,1fr));gap:14px;margin:36px 0 8px}
|
| 57 |
-
.stat{background:var(--panel);border:1px solid var(--line);border-radius:14px;padding:20px 18px}
|
| 58 |
-
.stat .n{font-family:var(--mono);font-size:clamp(23px,3.8vw,32px);font-weight:700;letter-spacing:-.02em;
|
| 59 |
-
color:var(--accent);font-variant-numeric:tabular-nums}
|
| 60 |
-
.stat.hero .n{color:var(--hero)}
|
| 61 |
-
.stat .l{font-size:13.5px;color:var(--muted);margin-top:7px}
|
| 62 |
-
.stat .l b{color:var(--ink);font-weight:600}
|
| 63 |
-
|
| 64 |
-
h2{font-size:13px;font-family:var(--mono);letter-spacing:.14em;text-transform:uppercase;
|
| 65 |
-
color:var(--muted);margin:44px 0 4px;font-weight:600}
|
| 66 |
-
.h2sub{font-size:14px;color:var(--muted);margin:0 0 16px}
|
| 67 |
-
.h2sub b{color:var(--ink)}
|
| 68 |
-
|
| 69 |
-
.tablecard{background:var(--panel);border:1px solid var(--line);border-radius:16px;overflow:hidden}
|
| 70 |
-
.scroll{overflow-x:auto}
|
| 71 |
-
table{border-collapse:collapse;width:100%;min-width:800px;font-size:14px}
|
| 72 |
-
thead th{font-family:var(--mono);font-size:11px;letter-spacing:.08em;text-transform:uppercase;
|
| 73 |
-
color:var(--muted);text-align:left;padding:14px 16px;border-bottom:1px solid var(--line);font-weight:600;white-space:nowrap}
|
| 74 |
-
thead th.r,tbody td.r{text-align:right}
|
| 75 |
-
tbody td{padding:14px 16px;border-bottom:1px solid var(--line);vertical-align:middle}
|
| 76 |
-
tbody tr:last-child td{border-bottom:none}
|
| 77 |
-
.mname{font-weight:600;font-size:14.5px;display:flex;align-items:center;gap:8px;flex-wrap:wrap}
|
| 78 |
-
.mname .star{color:var(--star)}
|
| 79 |
-
.lineage{font-size:11.5px;color:var(--muted);margin-top:3px;font-family:var(--mono)}
|
| 80 |
-
.gpqa{font-family:var(--mono);font-weight:700;font-size:16px;font-variant-numeric:tabular-nums}
|
| 81 |
-
.method{font-size:10.5px;color:var(--muted);margin-top:2px;letter-spacing:.01em}
|
| 82 |
-
.size{font-family:var(--mono);font-size:12.5px;color:var(--muted);font-variant-numeric:tabular-nums;white-space:nowrap}
|
| 83 |
-
.hw{font-size:12.5px;color:var(--muted);white-space:nowrap}
|
| 84 |
-
.vkue{font-family:var(--mono);font-weight:600;font-size:13px;color:var(--ink);white-space:nowrap}
|
| 85 |
-
.pill{display:inline-block;font-family:var(--mono);font-size:11px;padding:3px 9px;border-radius:999px;
|
| 86 |
-
background:var(--accent-soft);color:var(--accent);border:1px solid transparent;white-space:nowrap}
|
| 87 |
-
.pill.cpu{background:var(--good-soft);color:var(--good)}
|
| 88 |
-
tr.hero td{background:var(--hero-soft)}
|
| 89 |
-
tr.hero .gpqa,tr.hero .vkue{color:var(--hero)}
|
| 90 |
-
tr.hero .pill{background:transparent;border-color:var(--hero);color:var(--hero)}
|
| 91 |
-
tr.base td{opacity:.72}
|
| 92 |
-
.tag-hero{font-family:var(--mono);font-size:10px;padding:2px 7px;border-radius:5px;background:var(--hero);
|
| 93 |
-
color:#0B1418;font-weight:700;letter-spacing:.04em}
|
| 94 |
-
|
| 95 |
-
.legend{display:grid;grid-template-columns:repeat(auto-fit,minmax(240px,1fr));gap:10px 24px;
|
| 96 |
-
margin-top:20px;font-size:12.5px;color:var(--muted)}
|
| 97 |
-
.legend div b{color:var(--ink);font-weight:600}
|
| 98 |
-
.legend .k{font-family:var(--mono);color:var(--accent)}
|
| 99 |
-
|
| 100 |
-
.cols{display:grid;grid-template-columns:1fr 1fr;gap:14px;margin-top:16px}
|
| 101 |
-
.card{background:var(--panel);border:1px solid var(--line);border-radius:14px;padding:22px}
|
| 102 |
-
.card .t{font-family:var(--mono);font-weight:700;font-size:15px;margin:0 0 4px}
|
| 103 |
-
.card.a .t{color:var(--hero)} .card.b .t{color:var(--accent)}
|
| 104 |
-
.card p{margin:8px 0 0;font-size:13.5px;color:var(--muted)}
|
| 105 |
-
.card p b{color:var(--ink)}
|
| 106 |
-
.note{margin-top:16px;padding:14px 16px;border:1px dashed var(--line);border-radius:12px;
|
| 107 |
-
font-size:12.5px;color:var(--muted);background:var(--panel)}
|
| 108 |
-
.note b{color:var(--ink)}
|
| 109 |
-
footer{margin-top:40px;padding-top:20px;border-top:1px solid var(--line);
|
| 110 |
-
font-size:12px;color:var(--muted);font-family:var(--mono);display:flex;justify-content:space-between;flex-wrap:wrap;gap:8px}
|
| 111 |
-
@media (max-width:680px){.stats,.cols{grid-template-columns:1fr}}
|
| 112 |
-
</style>
|
| 113 |
-
|
| 114 |
-
<div class="wrap">
|
| 115 |
-
<p class="eyebrow">VIDRAFT · Inference Engine</p>
|
| 116 |
-
<h1 class="wordmark">VKUE<small>VIDRAFT Kernel Ubiquitous Engine</small></h1>
|
| 117 |
-
<p class="tagline">No GPU? Runs anyway. <b>Everywhere.</b> The ubiquity engine that serves frontier-class models on minimal hardware.</p>
|
| 118 |
-
<div class="sibs">
|
| 119 |
-
<a class="chip link" href="https://huggingface.co/spaces/VIDraft/vkae" target="_blank" rel="noopener"><b>VKAE</b> — Speed ↗</a>
|
| 120 |
-
<span class="chip now"><b>VKUE</b> — Ubiquity · Anywhere</span>
|
| 121 |
-
<a class="chip link" href="https://huggingface.co/spaces/FINAL-Bench/Ourbox-35B-VKUE-Demo" target="_blank" rel="noopener"><b>▶ Live: GPU vs CPU</b> ↗</a>
|
| 122 |
-
<a class="chip link" href="https://huggingface.co/spaces/FINAL-Bench/Ourbox-35B-VKUE-CPU" target="_blank" rel="noopener"><b>▶ Live: CPU-only</b> ↗</a>
|
| 123 |
-
<a class="chip link" href="https://huggingface.co/spaces/FINAL-Bench/Ourbox-35B-VKUE-FreeCPU" target="_blank" rel="noopener"><b>▶ Live: FREE CPU</b> ↗</a>
|
| 124 |
-
</div>
|
| 125 |
-
|
| 126 |
-
<div class="stats">
|
| 127 |
-
<div class="stat hero">
|
| 128 |
-
<div class="n">18,057 tok/s</div>
|
| 129 |
-
<div class="l">Ourbox-35B on a <b>single B200</b> — VKAE speed ceiling. <b>Measured</b>, aggregate.</div>
|
| 130 |
-
</div>
|
| 131 |
-
<div class="stat">
|
| 132 |
-
<div class="n">20 tok/s</div>
|
| 133 |
-
<div class="l"><b>Same model</b> on an <b>8 GB laptop</b> — VKUE ubiquity floor. <b>Measured</b>, 3.7× a dense 32B.</div>
|
| 134 |
-
</div>
|
| 135 |
-
<div class="stat">
|
| 136 |
-
<div class="n">FREE CPU</div>
|
| 137 |
-
<div class="l"><b>34.7B</b> on HuggingFace’s <b>free public CPU space</b> (2 vCPU) — <b>~
|
| 138 |
-
</div>
|
| 139 |
-
<div class="stat">
|
| 140 |
-
<div class="n">744B → 1 GPU</div>
|
| 141 |
-
<div class="l">Even <b>GLM-5.2</b>-class giants on a single <b>H100</b> (normally 6–8).</div>
|
| 142 |
-
</div>
|
| 143 |
-
<div class="stat">
|
| 144 |
-
<div class="n">90.9%</div>
|
| 145 |
-
<div class="l">Darwin-398B-JGOS top <b>GPQA Diamond</b> (greedy, no test-time engine).</div>
|
| 146 |
-
</div>
|
| 147 |
-
</div>
|
| 148 |
-
|
| 149 |
-
<h2>VKUE Efficiency Leaderboard</h2>
|
| 150 |
-
<p class="h2sub">How little hardware a given quality needs — <b>27B and up</b>. GPQA values are each model card’s posted figure (method noted).</p>
|
| 151 |
-
|
| 152 |
-
<div class="tablecard"><div class="scroll">
|
| 153 |
-
<table>
|
| 154 |
-
<thead>
|
| 155 |
-
<tr>
|
| 156 |
-
<th>Model</th>
|
| 157 |
-
<th class="r">GPQA Diamond</th>
|
| 158 |
-
<th class="r">Size (total / active)</th>
|
| 159 |
-
<th>Standard HW</th>
|
| 160 |
-
<th>VKUE Min HW</th>
|
| 161 |
-
</tr>
|
| 162 |
-
</thead>
|
| 163 |
-
<tbody>
|
| 164 |
-
<tr class="hero">
|
| 165 |
-
<td><div class="mname">GLM-5.2 <span class="tag-hero">SYMBOLIC</span></div><div class="lineage">Z.ai · 744B MoE · frontier</div></td>
|
| 166 |
-
<td class="r"><div class="gpqa">frontier</div><div class="method">official figure — citation pending</div></td>
|
| 167 |
-
<td class="r"><span class="size">744B / 40B</span></td>
|
| 168 |
-
<td><span class="hw">H100 ×6–8 (INT4)</span></td>
|
| 169 |
-
<td><span class="vkue">H100 ×1</span> <span class="pill">≈ 1/6–1/8</span><div class="method">capacity verified · speed pending</div></td>
|
| 170 |
-
</tr>
|
| 171 |
-
<tr>
|
| 172 |
-
<td><div class="mname">Darwin-398B-JGOS</div><div class="lineage">Darwin V9 · 397B MoE</div></td>
|
| 173 |
-
<td class="r"><div class="gpqa">90.9</div><div class="method">greedy · no engine</div></td>
|
| 174 |
-
<td class="r"><span class="size">397B / 17B</span></td>
|
| 175 |
-
<td><span class="hw">pure GPU ×3–4 (INT4)</span></td>
|
| 176 |
-
<td><span class="vkue">1 GPU + RAM</span> <span class="pill">available now</span></td>
|
| 177 |
-
</tr>
|
| 178 |
-
<tr>
|
| 179 |
-
<td><div class="mname">Darwin-28B-REASON</div><div class="lineage">Darwin · DELPHI engine</div></td>
|
| 180 |
-
<td class="r"><div class="gpqa">89.39</div><div class="method">maj · DELPHI engine</div></td>
|
| 181 |
-
<td class="r"><span class="size">26.9B</span></td>
|
| 182 |
-
<td><span class="hw">1 GPU</span></td>
|
| 183 |
-
<td><span class="vkue">24GB ×1</span> <span class="pill cpu">CPU-capable</span></td>
|
| 184 |
-
</tr>
|
| 185 |
-
<tr>
|
| 186 |
-
<td><div class="mname">Darwin-28B-Opus</div><div class="lineage">Darwin · 28B</div></td>
|
| 187 |
-
<td class="r"><div class="gpqa">88.89</div><div class="method">posted figure</div></td>
|
| 188 |
-
<td class="r"><span class="size">~28B</span></td>
|
| 189 |
-
<td><span class="hw">1 GPU</span></td>
|
| 190 |
-
<td><span class="vkue">24GB ×1</span> <span class="pill cpu">CPU-capable</span></td>
|
| 191 |
-
</tr>
|
| 192 |
-
<tr>
|
| 193 |
-
<td><div class="mname"><span class="star">★</span> Darwin-36B-Opus</div><div class="lineage">base ← Qwen3.6-35B-A3B</div></td>
|
| 194 |
-
<td class="r"><div class="gpqa">88.4</div><div class="method">GPQA Diamond</div></td>
|
| 195 |
-
<td class="r"><span class="size">36B / 3B</span></td>
|
| 196 |
-
<td><span class="hw">1 GPU (FP8)</span></td>
|
| 197 |
-
<td><span class="vkue">consumer 24GB ×1</span> <span class="pill cpu">CPU-capable</span></td>
|
| 198 |
-
</tr>
|
| 199 |
-
<tr>
|
| 200 |
-
<td><div class="mname">Darwin-27B-Opus</div><div class="lineage">Qwen3.5 · 27.8B</div></td>
|
| 201 |
-
<td class="r"><div class="gpqa">86.9</div><div class="method">posted figure</div></td>
|
| 202 |
-
<td class="r"><span class="size">27.8B</span></td>
|
| 203 |
-
<td><span class="hw">1 GPU</span></td>
|
| 204 |
-
<td><span class="vkue">24GB ×1</span> <span class="pill cpu">CPU-capable</span></td>
|
| 205 |
-
</tr>
|
| 206 |
-
<tr class="hero">
|
| 207 |
-
<td><div class="mname"><span class="star">★</span> Ourbox-35B-JGOS <span class="tag-hero">MEASURED</span></div><div class="lineage">Darwin-36B derivative · <a href="https://huggingface.co/FINAL-Bench/Ourbox-35B-JGOS-GGUF" style="color:inherit">GGUF ↗</a></div></td>
|
| 208 |
-
<td class="r"><div class="gpqa">86.4 / 70.7</div><div class="method">maj@8 / greedy (measured)</div></td>
|
| 209 |
-
<td class="r"><span class="size">35B / 3B</span></td>
|
| 210 |
-
<td><span class="hw">1 GPU (FP8)</span></td>
|
| 211 |
-
<td><span class="vkue">A10G 126 · CPU 17 tok/s</span> <a class="pill cpu" href="https://huggingface.co/spaces/FINAL-Bench/Ourbox-35B-VKUE-Demo" target="_blank" rel="noopener" style="text-decoration:none">live demo ↗</a><div class="method">live measured · also 8GB laptop 20 tok/s (3.7× dense 32B)</div></td>
|
| 212 |
-
</tr>
|
| 213 |
-
<tr>
|
| 214 |
-
<td><div class="mname">Darwin-31B-Opus</div><div class="lineage">base ← Gemma4-31B · Korean #1</div></td>
|
| 215 |
-
<td class="r"><div class="gpqa">85.9</div><div class="method">posted figure</div></td>
|
| 216 |
-
<td class="r"><span class="size">32.7B</span></td>
|
| 217 |
-
<td><span class="hw">1 GPU</span></td>
|
| 218 |
-
<td><span class="vkue">consumer 24GB ×1</span> <span class="pill cpu">CPU-capable</span></td>
|
| 219 |
-
</tr>
|
| 220 |
-
<tr class="base">
|
| 221 |
-
<td><div class="mname">Qwen3.6-35B-A3B</div><div class="lineage">base model · Darwin-36B parent</div></td>
|
| 222 |
-
<td class="r"><div class="gpqa">—</div><div class="method">official figure — pending</div></td>
|
| 223 |
-
<td class="r"><span class="size">35B / 3B</span></td>
|
| 224 |
-
<td><span class="hw">1 GPU (FP8)</span></td>
|
| 225 |
-
<td><span class="vkue">consumer 24GB ×1</span></td>
|
| 226 |
-
</tr>
|
| 227 |
-
<tr class="base">
|
| 228 |
-
<td><div class="mname">Gemma4-31B</div><div class="lineage">base model · Darwin-31B parent</div></td>
|
| 229 |
-
<td class="r"><div class="gpqa">—</div><div class="method">official figure — pending</div></td>
|
| 230 |
-
<td class="r"><span class="size">31B</span></td>
|
| 231 |
-
<td><span class="hw">1 GPU</span></td>
|
| 232 |
-
<td><span class="vkue">consumer 24GB ×1</span></td>
|
| 233 |
-
</tr>
|
| 234 |
-
</tbody>
|
| 235 |
-
</table>
|
| 236 |
-
</div></div>
|
| 237 |
-
|
| 238 |
-
<div class="legend">
|
| 239 |
-
<div><span class="k">Method labels</span> · <b>greedy</b> = single pass, <b>maj@8</b> = majority of 8 samples, <b>DELPHI</b> = our test-time engine. Different conditions — not directly comparable.</div>
|
| 240 |
-
<div><span class="k">VKUE Min HW</span> · INT4, held fully in VRAM or served with little / no GPU. <b>CPU-capable</b> = runs without a GPU (slower) thanks to ~3B active params.</div>
|
| 241 |
-
<div><span class="k">Throughput (tok/s)</span> · Ourbox-35B measured: <b>18,057</b> aggregate on B200 (<a class="tlink" href="https://huggingface.co/spaces/VIDraft/vkae" target="_blank" rel="noopener" style="color:var(--accent)">VKAE ↗</a>) / <b>126</b> on one A10G & <b>17</b> on a GPU-less CPU box (<a class="tlink" href="https://huggingface.co/spaces/FINAL-Bench/Ourbox-35B-VKUE-Demo" target="_blank" rel="noopener" style="color:var(--accent)">live demo ↗</a>) / <b>20</b> on an 8GB laptop. All single-stream, generate-format–gated.</div>
|
| 242 |
-
<div><span class="k">Base models</span> · Qwen3.6-35B / Gemma4-31B are our bases; their GPQA figures will be cited from official sources.</div>
|
| 243 |
-
</div>
|
| 244 |
-
|
| 245 |
-
<h2>Engine Siblings</h2>
|
| 246 |
-
<div class="cols">
|
| 247 |
-
<div class="card a">
|
| 248 |
-
<p class="t"><a class="tlink" href="https://huggingface.co/spaces/VIDraft/vkae" target="_blank" rel="noopener" style="color:inherit">VKAE — Speed ↗</a></p>
|
| 249 |
-
<p><b>How fast.</b> VIDRAFT-optimized serving pushes throughput to the ceiling — Ourbox-35B <b>measured at 18,057 tok/s</b> aggregate on a single <b>B200</b>. <a class="tlink" href="https://huggingface.co/spaces/VIDraft/vkae" target="_blank" rel="noopener" style="color:var(--accent)">Open the Speed leaderboard ↗</a></p>
|
| 250 |
-
</div>
|
| 251 |
-
<div class="card b">
|
| 252 |
-
<p class="t"><a class="tlink" href="https://huggingface.co/spaces/FINAL-Bench/Ourbox-35B-VKUE-Demo" target="_blank" rel="noopener" style="color:inherit">VKUE — Ubiquity ↗</a></p>
|
| 253 |
-
<p><b>How low the bar.</b> Same 34.7B model, minimal hardware — <b>live measured 126 tok/s on one A10G</b> vs <b>17 tok/s on a GPU-less CPU box</b> (identical weights, only the hardware differs), and <b>20 tok/s</b> on an 8 GB laptop. If you have a card it’s fast; if you don’t, it still runs. <a class="tlink" href="https://huggingface.co/spaces/FINAL-Bench/Ourbox-35B-VKUE-Demo" target="_blank" rel="noopener" style="color:var(--accent)">Try the live GPU vs CPU demo ↗</a></p>
|
| 254 |
-
</div>
|
| 255 |
-
</div>
|
| 256 |
-
|
| 257 |
-
<div class="note">
|
| 258 |
-
<b>What’s open.</b> Quantized models, benchmark figures, and open-tool run instructions are public — anyone can reproduce the baseline.
|
| 259 |
-
VKUE’s engine internals are proprietary; this leaderboard reports only the resulting hardware, never the how.
|
| 260 |
-
</div>
|
| 261 |
-
|
| 262 |
-
<footer>
|
| 263 |
-
<span>FINAL-Bench · VIDRAFT</span>
|
| 264 |
-
<span>2026 · VKUE v1 preview</span>
|
| 265 |
-
</footer>
|
| 266 |
-
</div>
|
| 267 |
-
|
| 268 |
-
</body>
|
| 269 |
-
</html>
|
|
|
|
| 1 |
+
<!doctype html>
|
| 2 |
+
<html lang="en">
|
| 3 |
+
<head>
|
| 4 |
+
<meta charset="utf-8">
|
| 5 |
+
<meta name="viewport" content="width=device-width, initial-scale=1">
|
| 6 |
+
<title>VKUE — VIDRAFT Kernel Ubiquitous Engine</title>
|
| 7 |
+
<meta name="description" content="VKUE Efficiency Leaderboard — serve frontier-class models on minimal hardware.">
|
| 8 |
+
</head>
|
| 9 |
+
<body>
|
| 10 |
+
<style>
|
| 11 |
+
:root{
|
| 12 |
+
--ground:#F4F7F7; --panel:#FFFFFF; --ink:#0B1418; --muted:#5B6B70;
|
| 13 |
+
--line:#D7E0E1; --accent:#0E8C9E; --accent-soft:#E2F4F6; --hero:#B0791A;
|
| 14 |
+
--hero-soft:#FBF1DE; --good:#1F8A5B; --good-soft:#E4F3EC; --star:#0E8C9E;
|
| 15 |
+
--mono:ui-monospace,"SFMono-Regular","Cascadia Code","Consolas",monospace;
|
| 16 |
+
--sans:-apple-system,BlinkMacSystemFont,"Segoe UI","Apple SD Gothic Neo","Malgun Gothic",Roboto,sans-serif;
|
| 17 |
+
}
|
| 18 |
+
@media (prefers-color-scheme:dark){
|
| 19 |
+
:root{
|
| 20 |
+
--ground:#0B1418; --panel:#111E23; --ink:#E6EFF0; --muted:#8CA1A6;
|
| 21 |
+
--line:#22343A; --accent:#22B8CF; --accent-soft:#0F2A31; --hero:#E0A83E;
|
| 22 |
+
--hero-soft:#2A2113; --good:#43D08A; --good-soft:#10281D; --star:#22B8CF;
|
| 23 |
+
}
|
| 24 |
+
}
|
| 25 |
+
:root[data-theme="light"]{
|
| 26 |
+
--ground:#F4F7F7; --panel:#FFFFFF; --ink:#0B1418; --muted:#5B6B70;
|
| 27 |
+
--line:#D7E0E1; --accent:#0E8C9E; --accent-soft:#E2F4F6; --hero:#B0791A;
|
| 28 |
+
--hero-soft:#FBF1DE; --good:#1F8A5B; --good-soft:#E4F3EC; --star:#0E8C9E;
|
| 29 |
+
}
|
| 30 |
+
:root[data-theme="dark"]{
|
| 31 |
+
--ground:#0B1418; --panel:#111E23; --ink:#E6EFF0; --muted:#8CA1A6;
|
| 32 |
+
--line:#22343A; --accent:#22B8CF; --accent-soft:#0F2A31; --hero:#E0A83E;
|
| 33 |
+
--hero-soft:#2A2113; --good:#43D08A; --good-soft:#10281D; --star:#22B8CF;
|
| 34 |
+
}
|
| 35 |
+
*{box-sizing:border-box}
|
| 36 |
+
body{margin:0;background:var(--ground);color:var(--ink);font-family:var(--sans);
|
| 37 |
+
line-height:1.5;-webkit-font-smoothing:antialiased}
|
| 38 |
+
.wrap{max-width:1060px;margin:0 auto;padding:clamp(20px,4vw,52px) clamp(16px,4vw,40px)}
|
| 39 |
+
.eyebrow{font-family:var(--mono);font-size:12px;letter-spacing:.22em;text-transform:uppercase;
|
| 40 |
+
color:var(--accent);margin:0 0 14px}
|
| 41 |
+
.wordmark{font-family:var(--mono);font-weight:700;font-size:clamp(38px,8vw,68px);
|
| 42 |
+
letter-spacing:-.01em;margin:0;line-height:.98;text-wrap:balance}
|
| 43 |
+
.wordmark small{color:var(--muted);font-weight:400;font-size:.30em;letter-spacing:.02em;display:block;margin-top:12px}
|
| 44 |
+
.tagline{font-size:clamp(17px,2.4vw,22px);color:var(--ink);margin:18px 0 0;max-width:52ch;text-wrap:balance}
|
| 45 |
+
.tagline b{color:var(--accent)}
|
| 46 |
+
.sibs{display:flex;flex-wrap:wrap;gap:10px;margin-top:22px}
|
| 47 |
+
.chip{font-family:var(--mono);font-size:12.5px;padding:7px 13px;border:1px solid var(--line);
|
| 48 |
+
border-radius:999px;color:var(--muted);background:var(--panel)}
|
| 49 |
+
.chip b{color:var(--ink)}
|
| 50 |
+
.chip.now{border-color:var(--accent);color:var(--accent)}
|
| 51 |
+
.chip.link{text-decoration:none;cursor:pointer;transition:border-color .15s,color .15s}
|
| 52 |
+
.chip.link:hover{border-color:var(--accent);color:var(--accent)}
|
| 53 |
+
.card a.tlink{text-decoration:none}
|
| 54 |
+
.card a.tlink:hover{text-decoration:underline}
|
| 55 |
+
|
| 56 |
+
.stats{display:grid;grid-template-columns:repeat(auto-fit,minmax(198px,1fr));gap:14px;margin:36px 0 8px}
|
| 57 |
+
.stat{background:var(--panel);border:1px solid var(--line);border-radius:14px;padding:20px 18px}
|
| 58 |
+
.stat .n{font-family:var(--mono);font-size:clamp(23px,3.8vw,32px);font-weight:700;letter-spacing:-.02em;
|
| 59 |
+
color:var(--accent);font-variant-numeric:tabular-nums}
|
| 60 |
+
.stat.hero .n{color:var(--hero)}
|
| 61 |
+
.stat .l{font-size:13.5px;color:var(--muted);margin-top:7px}
|
| 62 |
+
.stat .l b{color:var(--ink);font-weight:600}
|
| 63 |
+
|
| 64 |
+
h2{font-size:13px;font-family:var(--mono);letter-spacing:.14em;text-transform:uppercase;
|
| 65 |
+
color:var(--muted);margin:44px 0 4px;font-weight:600}
|
| 66 |
+
.h2sub{font-size:14px;color:var(--muted);margin:0 0 16px}
|
| 67 |
+
.h2sub b{color:var(--ink)}
|
| 68 |
+
|
| 69 |
+
.tablecard{background:var(--panel);border:1px solid var(--line);border-radius:16px;overflow:hidden}
|
| 70 |
+
.scroll{overflow-x:auto}
|
| 71 |
+
table{border-collapse:collapse;width:100%;min-width:800px;font-size:14px}
|
| 72 |
+
thead th{font-family:var(--mono);font-size:11px;letter-spacing:.08em;text-transform:uppercase;
|
| 73 |
+
color:var(--muted);text-align:left;padding:14px 16px;border-bottom:1px solid var(--line);font-weight:600;white-space:nowrap}
|
| 74 |
+
thead th.r,tbody td.r{text-align:right}
|
| 75 |
+
tbody td{padding:14px 16px;border-bottom:1px solid var(--line);vertical-align:middle}
|
| 76 |
+
tbody tr:last-child td{border-bottom:none}
|
| 77 |
+
.mname{font-weight:600;font-size:14.5px;display:flex;align-items:center;gap:8px;flex-wrap:wrap}
|
| 78 |
+
.mname .star{color:var(--star)}
|
| 79 |
+
.lineage{font-size:11.5px;color:var(--muted);margin-top:3px;font-family:var(--mono)}
|
| 80 |
+
.gpqa{font-family:var(--mono);font-weight:700;font-size:16px;font-variant-numeric:tabular-nums}
|
| 81 |
+
.method{font-size:10.5px;color:var(--muted);margin-top:2px;letter-spacing:.01em}
|
| 82 |
+
.size{font-family:var(--mono);font-size:12.5px;color:var(--muted);font-variant-numeric:tabular-nums;white-space:nowrap}
|
| 83 |
+
.hw{font-size:12.5px;color:var(--muted);white-space:nowrap}
|
| 84 |
+
.vkue{font-family:var(--mono);font-weight:600;font-size:13px;color:var(--ink);white-space:nowrap}
|
| 85 |
+
.pill{display:inline-block;font-family:var(--mono);font-size:11px;padding:3px 9px;border-radius:999px;
|
| 86 |
+
background:var(--accent-soft);color:var(--accent);border:1px solid transparent;white-space:nowrap}
|
| 87 |
+
.pill.cpu{background:var(--good-soft);color:var(--good)}
|
| 88 |
+
tr.hero td{background:var(--hero-soft)}
|
| 89 |
+
tr.hero .gpqa,tr.hero .vkue{color:var(--hero)}
|
| 90 |
+
tr.hero .pill{background:transparent;border-color:var(--hero);color:var(--hero)}
|
| 91 |
+
tr.base td{opacity:.72}
|
| 92 |
+
.tag-hero{font-family:var(--mono);font-size:10px;padding:2px 7px;border-radius:5px;background:var(--hero);
|
| 93 |
+
color:#0B1418;font-weight:700;letter-spacing:.04em}
|
| 94 |
+
|
| 95 |
+
.legend{display:grid;grid-template-columns:repeat(auto-fit,minmax(240px,1fr));gap:10px 24px;
|
| 96 |
+
margin-top:20px;font-size:12.5px;color:var(--muted)}
|
| 97 |
+
.legend div b{color:var(--ink);font-weight:600}
|
| 98 |
+
.legend .k{font-family:var(--mono);color:var(--accent)}
|
| 99 |
+
|
| 100 |
+
.cols{display:grid;grid-template-columns:1fr 1fr;gap:14px;margin-top:16px}
|
| 101 |
+
.card{background:var(--panel);border:1px solid var(--line);border-radius:14px;padding:22px}
|
| 102 |
+
.card .t{font-family:var(--mono);font-weight:700;font-size:15px;margin:0 0 4px}
|
| 103 |
+
.card.a .t{color:var(--hero)} .card.b .t{color:var(--accent)}
|
| 104 |
+
.card p{margin:8px 0 0;font-size:13.5px;color:var(--muted)}
|
| 105 |
+
.card p b{color:var(--ink)}
|
| 106 |
+
.note{margin-top:16px;padding:14px 16px;border:1px dashed var(--line);border-radius:12px;
|
| 107 |
+
font-size:12.5px;color:var(--muted);background:var(--panel)}
|
| 108 |
+
.note b{color:var(--ink)}
|
| 109 |
+
footer{margin-top:40px;padding-top:20px;border-top:1px solid var(--line);
|
| 110 |
+
font-size:12px;color:var(--muted);font-family:var(--mono);display:flex;justify-content:space-between;flex-wrap:wrap;gap:8px}
|
| 111 |
+
@media (max-width:680px){.stats,.cols{grid-template-columns:1fr}}
|
| 112 |
+
</style>
|
| 113 |
+
|
| 114 |
+
<div class="wrap">
|
| 115 |
+
<p class="eyebrow">VIDRAFT · Inference Engine</p>
|
| 116 |
+
<h1 class="wordmark">VKUE<small>VIDRAFT Kernel Ubiquitous Engine</small></h1>
|
| 117 |
+
<p class="tagline">No GPU? Runs anyway. <b>Everywhere.</b> The ubiquity engine that serves frontier-class models on minimal hardware.</p>
|
| 118 |
+
<div class="sibs">
|
| 119 |
+
<a class="chip link" href="https://huggingface.co/spaces/VIDraft/vkae" target="_blank" rel="noopener"><b>VKAE</b> — Speed ↗</a>
|
| 120 |
+
<span class="chip now"><b>VKUE</b> — Ubiquity · Anywhere</span>
|
| 121 |
+
<a class="chip link" href="https://huggingface.co/spaces/FINAL-Bench/Ourbox-35B-VKUE-Demo" target="_blank" rel="noopener"><b>▶ Live: GPU vs CPU</b> ↗</a>
|
| 122 |
+
<a class="chip link" href="https://huggingface.co/spaces/FINAL-Bench/Ourbox-35B-VKUE-CPU" target="_blank" rel="noopener"><b>▶ Live: CPU-only</b> ↗</a>
|
| 123 |
+
<a class="chip link" href="https://huggingface.co/spaces/FINAL-Bench/Ourbox-35B-VKUE-FreeCPU" target="_blank" rel="noopener"><b>▶ Live: FREE CPU</b> ↗</a>
|
| 124 |
+
</div>
|
| 125 |
+
|
| 126 |
+
<div class="stats">
|
| 127 |
+
<div class="stat hero">
|
| 128 |
+
<div class="n">18,057 tok/s</div>
|
| 129 |
+
<div class="l">Ourbox-35B on a <b>single B200</b> — VKAE speed ceiling. <b>Measured</b>, aggregate.</div>
|
| 130 |
+
</div>
|
| 131 |
+
<div class="stat">
|
| 132 |
+
<div class="n">20 tok/s</div>
|
| 133 |
+
<div class="l"><b>Same model</b> on an <b>8 GB laptop</b> — VKUE ubiquity floor. <b>Measured</b>, 3.7× a dense 32B.</div>
|
| 134 |
+
</div>
|
| 135 |
+
<div class="stat">
|
| 136 |
+
<div class="n">FREE CPU</div>
|
| 137 |
+
<div class="l"><b>34.7B</b> on HuggingFace’s <b>free public CPU space</b> (2 vCPU) — <b>~6-7 tok/s</b>, zero cost. <a class="tlink" href="https://huggingface.co/spaces/FINAL-Bench/Ourbox-35B-VKUE-FreeCPU" target="_blank" rel="noopener" style="color:var(--accent)">Try it ↗</a></div>
|
| 138 |
+
</div>
|
| 139 |
+
<div class="stat">
|
| 140 |
+
<div class="n">744B → 1 GPU</div>
|
| 141 |
+
<div class="l">Even <b>GLM-5.2</b>-class giants on a single <b>H100</b> (normally 6–8).</div>
|
| 142 |
+
</div>
|
| 143 |
+
<div class="stat">
|
| 144 |
+
<div class="n">90.9%</div>
|
| 145 |
+
<div class="l">Darwin-398B-JGOS top <b>GPQA Diamond</b> (greedy, no test-time engine).</div>
|
| 146 |
+
</div>
|
| 147 |
+
</div>
|
| 148 |
+
|
| 149 |
+
<h2>VKUE Efficiency Leaderboard</h2>
|
| 150 |
+
<p class="h2sub">How little hardware a given quality needs — <b>27B and up</b>. GPQA values are each model card’s posted figure (method noted).</p>
|
| 151 |
+
|
| 152 |
+
<div class="tablecard"><div class="scroll">
|
| 153 |
+
<table>
|
| 154 |
+
<thead>
|
| 155 |
+
<tr>
|
| 156 |
+
<th>Model</th>
|
| 157 |
+
<th class="r">GPQA Diamond</th>
|
| 158 |
+
<th class="r">Size (total / active)</th>
|
| 159 |
+
<th>Standard HW</th>
|
| 160 |
+
<th>VKUE Min HW</th>
|
| 161 |
+
</tr>
|
| 162 |
+
</thead>
|
| 163 |
+
<tbody>
|
| 164 |
+
<tr class="hero">
|
| 165 |
+
<td><div class="mname">GLM-5.2 <span class="tag-hero">SYMBOLIC</span></div><div class="lineage">Z.ai · 744B MoE · frontier</div></td>
|
| 166 |
+
<td class="r"><div class="gpqa">frontier</div><div class="method">official figure — citation pending</div></td>
|
| 167 |
+
<td class="r"><span class="size">744B / 40B</span></td>
|
| 168 |
+
<td><span class="hw">H100 ×6–8 (INT4)</span></td>
|
| 169 |
+
<td><span class="vkue">H100 ×1</span> <span class="pill">≈ 1/6–1/8</span><div class="method">capacity verified · speed pending</div></td>
|
| 170 |
+
</tr>
|
| 171 |
+
<tr>
|
| 172 |
+
<td><div class="mname">Darwin-398B-JGOS</div><div class="lineage">Darwin V9 · 397B MoE</div></td>
|
| 173 |
+
<td class="r"><div class="gpqa">90.9</div><div class="method">greedy · no engine</div></td>
|
| 174 |
+
<td class="r"><span class="size">397B / 17B</span></td>
|
| 175 |
+
<td><span class="hw">pure GPU ×3–4 (INT4)</span></td>
|
| 176 |
+
<td><span class="vkue">1 GPU + RAM</span> <span class="pill">available now</span></td>
|
| 177 |
+
</tr>
|
| 178 |
+
<tr>
|
| 179 |
+
<td><div class="mname">Darwin-28B-REASON</div><div class="lineage">Darwin · DELPHI engine</div></td>
|
| 180 |
+
<td class="r"><div class="gpqa">89.39</div><div class="method">maj · DELPHI engine</div></td>
|
| 181 |
+
<td class="r"><span class="size">26.9B</span></td>
|
| 182 |
+
<td><span class="hw">1 GPU</span></td>
|
| 183 |
+
<td><span class="vkue">24GB ×1</span> <span class="pill cpu">CPU-capable</span></td>
|
| 184 |
+
</tr>
|
| 185 |
+
<tr>
|
| 186 |
+
<td><div class="mname">Darwin-28B-Opus</div><div class="lineage">Darwin · 28B</div></td>
|
| 187 |
+
<td class="r"><div class="gpqa">88.89</div><div class="method">posted figure</div></td>
|
| 188 |
+
<td class="r"><span class="size">~28B</span></td>
|
| 189 |
+
<td><span class="hw">1 GPU</span></td>
|
| 190 |
+
<td><span class="vkue">24GB ×1</span> <span class="pill cpu">CPU-capable</span></td>
|
| 191 |
+
</tr>
|
| 192 |
+
<tr>
|
| 193 |
+
<td><div class="mname"><span class="star">★</span> Darwin-36B-Opus</div><div class="lineage">base ← Qwen3.6-35B-A3B</div></td>
|
| 194 |
+
<td class="r"><div class="gpqa">88.4</div><div class="method">GPQA Diamond</div></td>
|
| 195 |
+
<td class="r"><span class="size">36B / 3B</span></td>
|
| 196 |
+
<td><span class="hw">1 GPU (FP8)</span></td>
|
| 197 |
+
<td><span class="vkue">consumer 24GB ×1</span> <span class="pill cpu">CPU-capable</span></td>
|
| 198 |
+
</tr>
|
| 199 |
+
<tr>
|
| 200 |
+
<td><div class="mname">Darwin-27B-Opus</div><div class="lineage">Qwen3.5 · 27.8B</div></td>
|
| 201 |
+
<td class="r"><div class="gpqa">86.9</div><div class="method">posted figure</div></td>
|
| 202 |
+
<td class="r"><span class="size">27.8B</span></td>
|
| 203 |
+
<td><span class="hw">1 GPU</span></td>
|
| 204 |
+
<td><span class="vkue">24GB ×1</span> <span class="pill cpu">CPU-capable</span></td>
|
| 205 |
+
</tr>
|
| 206 |
+
<tr class="hero">
|
| 207 |
+
<td><div class="mname"><span class="star">★</span> Ourbox-35B-JGOS <span class="tag-hero">MEASURED</span></div><div class="lineage">Darwin-36B derivative · <a href="https://huggingface.co/FINAL-Bench/Ourbox-35B-JGOS-GGUF" style="color:inherit">GGUF ↗</a></div></td>
|
| 208 |
+
<td class="r"><div class="gpqa">86.4 / 70.7</div><div class="method">maj@8 / greedy (measured)</div></td>
|
| 209 |
+
<td class="r"><span class="size">35B / 3B</span></td>
|
| 210 |
+
<td><span class="hw">1 GPU (FP8)</span></td>
|
| 211 |
+
<td><span class="vkue">A10G 126 · CPU 17 tok/s</span> <a class="pill cpu" href="https://huggingface.co/spaces/FINAL-Bench/Ourbox-35B-VKUE-Demo" target="_blank" rel="noopener" style="text-decoration:none">live demo ↗</a><div class="method">live measured · also 8GB laptop 20 tok/s (3.7× dense 32B)</div></td>
|
| 212 |
+
</tr>
|
| 213 |
+
<tr>
|
| 214 |
+
<td><div class="mname">Darwin-31B-Opus</div><div class="lineage">base ← Gemma4-31B · Korean #1</div></td>
|
| 215 |
+
<td class="r"><div class="gpqa">85.9</div><div class="method">posted figure</div></td>
|
| 216 |
+
<td class="r"><span class="size">32.7B</span></td>
|
| 217 |
+
<td><span class="hw">1 GPU</span></td>
|
| 218 |
+
<td><span class="vkue">consumer 24GB ×1</span> <span class="pill cpu">CPU-capable</span></td>
|
| 219 |
+
</tr>
|
| 220 |
+
<tr class="base">
|
| 221 |
+
<td><div class="mname">Qwen3.6-35B-A3B</div><div class="lineage">base model · Darwin-36B parent</div></td>
|
| 222 |
+
<td class="r"><div class="gpqa">—</div><div class="method">official figure — pending</div></td>
|
| 223 |
+
<td class="r"><span class="size">35B / 3B</span></td>
|
| 224 |
+
<td><span class="hw">1 GPU (FP8)</span></td>
|
| 225 |
+
<td><span class="vkue">consumer 24GB ×1</span></td>
|
| 226 |
+
</tr>
|
| 227 |
+
<tr class="base">
|
| 228 |
+
<td><div class="mname">Gemma4-31B</div><div class="lineage">base model · Darwin-31B parent</div></td>
|
| 229 |
+
<td class="r"><div class="gpqa">—</div><div class="method">official figure — pending</div></td>
|
| 230 |
+
<td class="r"><span class="size">31B</span></td>
|
| 231 |
+
<td><span class="hw">1 GPU</span></td>
|
| 232 |
+
<td><span class="vkue">consumer 24GB ×1</span></td>
|
| 233 |
+
</tr>
|
| 234 |
+
</tbody>
|
| 235 |
+
</table>
|
| 236 |
+
</div></div>
|
| 237 |
+
|
| 238 |
+
<div class="legend">
|
| 239 |
+
<div><span class="k">Method labels</span> · <b>greedy</b> = single pass, <b>maj@8</b> = majority of 8 samples, <b>DELPHI</b> = our test-time engine. Different conditions — not directly comparable.</div>
|
| 240 |
+
<div><span class="k">VKUE Min HW</span> · INT4, held fully in VRAM or served with little / no GPU. <b>CPU-capable</b> = runs without a GPU (slower) thanks to ~3B active params.</div>
|
| 241 |
+
<div><span class="k">Throughput (tok/s)</span> · Ourbox-35B measured: <b>18,057</b> aggregate on B200 (<a class="tlink" href="https://huggingface.co/spaces/VIDraft/vkae" target="_blank" rel="noopener" style="color:var(--accent)">VKAE ↗</a>) / <b>126</b> on one A10G & <b>17</b> on a GPU-less CPU box (<a class="tlink" href="https://huggingface.co/spaces/FINAL-Bench/Ourbox-35B-VKUE-Demo" target="_blank" rel="noopener" style="color:var(--accent)">live demo ↗</a>) / <b>20</b> on an 8GB laptop. All single-stream, generate-format–gated.</div>
|
| 242 |
+
<div><span class="k">Base models</span> · Qwen3.6-35B / Gemma4-31B are our bases; their GPQA figures will be cited from official sources.</div>
|
| 243 |
+
</div>
|
| 244 |
+
|
| 245 |
+
<h2>Engine Siblings</h2>
|
| 246 |
+
<div class="cols">
|
| 247 |
+
<div class="card a">
|
| 248 |
+
<p class="t"><a class="tlink" href="https://huggingface.co/spaces/VIDraft/vkae" target="_blank" rel="noopener" style="color:inherit">VKAE — Speed ↗</a></p>
|
| 249 |
+
<p><b>How fast.</b> VIDRAFT-optimized serving pushes throughput to the ceiling — Ourbox-35B <b>measured at 18,057 tok/s</b> aggregate on a single <b>B200</b>. <a class="tlink" href="https://huggingface.co/spaces/VIDraft/vkae" target="_blank" rel="noopener" style="color:var(--accent)">Open the Speed leaderboard ↗</a></p>
|
| 250 |
+
</div>
|
| 251 |
+
<div class="card b">
|
| 252 |
+
<p class="t"><a class="tlink" href="https://huggingface.co/spaces/FINAL-Bench/Ourbox-35B-VKUE-Demo" target="_blank" rel="noopener" style="color:inherit">VKUE — Ubiquity ↗</a></p>
|
| 253 |
+
<p><b>How low the bar.</b> Same 34.7B model, minimal hardware — <b>live measured 126 tok/s on one A10G</b> vs <b>17 tok/s on a GPU-less CPU box</b> (identical weights, only the hardware differs), and <b>20 tok/s</b> on an 8 GB laptop. If you have a card it’s fast; if you don’t, it still runs. <a class="tlink" href="https://huggingface.co/spaces/FINAL-Bench/Ourbox-35B-VKUE-Demo" target="_blank" rel="noopener" style="color:var(--accent)">Try the live GPU vs CPU demo ↗</a></p>
|
| 254 |
+
</div>
|
| 255 |
+
</div>
|
| 256 |
+
|
| 257 |
+
<div class="note">
|
| 258 |
+
<b>What’s open.</b> Quantized models, benchmark figures, and open-tool run instructions are public — anyone can reproduce the baseline.
|
| 259 |
+
VKUE’s engine internals are proprietary; this leaderboard reports only the resulting hardware, never the how.
|
| 260 |
+
</div>
|
| 261 |
+
|
| 262 |
+
<footer>
|
| 263 |
+
<span>FINAL-Bench · VIDRAFT</span>
|
| 264 |
+
<span>2026 · VKUE v1 preview</span>
|
| 265 |
+
</footer>
|
| 266 |
+
</div>
|
| 267 |
+
|
| 268 |
+
</body>
|
| 269 |
+
</html>
|