Download index.html from Mast-LLM/README: direct link, hf CLI and curl.
- Browser
- Download file 4.84 kB
-
https://huggingface.co/spaces/Mast-LLM/README/resolve/main/index.html
- Command line
-
hf download hf://spaces/Mast-LLM/README/index.html
-
curl -L -o index.html https://huggingface.co/spaces/Mast-LLM/README/resolve/main/index.html
4.84 kB
| <html lang="en"> | |
| <head> | |
| <meta charset="utf-8"> | |
| <meta name="viewport" content="width=device-width, initial-scale=1"> | |
| <title>MastLLM</title> | |
| <style> | |
| :root{--bg:#0F2A1E;--panel:#0A1F16;--raised:#163526;--text:#E7F0E9;--muted:#9DB5A6;--green:#B6E33C;--line:#21442F} | |
| *{box-sizing:border-box;margin:0} | |
| body{background:var(--bg);color:var(--text);font:16px/1.55 system-ui,-apple-system,"Segoe UI",Roboto,sans-serif;padding:16px} | |
| .wrap{max-width:1100px;margin:0 auto} | |
| .banner{display:block;width:100%;height:auto;border-radius:16px;border:1px solid var(--line)} | |
| h1{font-size:30px;margin:28px 0 8px;letter-spacing:-.01em} | |
| h2{font-size:20px;margin:32px 0 12px} | |
| p{color:var(--muted);max-width:760px} | |
| .cards{display:grid;grid-template-columns:repeat(auto-fit,minmax(260px,1fr));gap:14px;margin-top:14px} | |
| .card{display:block;background:var(--panel);border:1px solid var(--line);border-radius:14px;padding:18px 20px;color:var(--text);text-decoration:none;transition:border-color .15s,transform .15s} | |
| .card:hover{border-color:var(--green);transform:translateY(-2px)} | |
| .card b{display:block;font-size:19px} | |
| .card span{display:block;color:var(--muted);font-size:15px;margin-top:6px} | |
| .card em{display:block;font-style:normal;color:var(--green);font-family:ui-monospace,Menlo,Consolas,monospace;font-size:14px;margin-top:12px} | |
| .links{display:flex;flex-wrap:wrap;gap:10px;margin-top:6px} | |
| .links a{background:var(--raised);border:1px solid #2C5A3C;border-radius:999px;padding:8px 18px;color:var(--text);text-decoration:none;font-size:15px} | |
| .links a:hover{border-color:var(--green)} | |
| .note{font-size:14px;margin-top:14px} | |
| footer{margin-top:40px;padding-top:18px;border-top:1px solid var(--line);color:var(--muted);font-size:14px} | |
| a.mail{color:var(--green)} | |
| @media (prefers-reduced-motion:reduce){.card{transition:none}} | |
| </style> | |
| </head> | |
| <body> | |
| <div class="wrap"> | |
| <img class="banner" src="https://huggingface.co/spaces/Mast-LLM/README/resolve/main/banner.png" alt="MastLLM: other labs keep building bigger, we build small"> | |
| <h1>MastLLM</h1> | |
| <p><strong style="color:var(--text)">Other labs keep building bigger. We build small.</strong> MastLLM makes compact, open AI models that run on the hardware you already own, and the apps that put them to work. The Mast family of sub-1B models is coming soon.</p> | |
| <h2>openTARS, our flagship</h2> | |
| <p><strong style="color:var(--text)">openTARS is an open source AI assistant that runs on your own computer.</strong> Ask in your own words: it opens programs, clicks buttons by their name, types, searches the web, runs commands and looks at your screen. By default nothing leaves your machine, and there is no account or subscription. It runs on Linux, Windows and macOS.</p> | |
| <h2>openTARS models</h2> | |
| <div class="cards"> | |
| <a class="card" href="https://huggingface.co/Mast-LLM/Gargantua-2.5"><b>Gargantua 2.5</b><span>The main model, on Gemma 4 E4B, with vision and audio.</span><em>4.9 GB + 0.99 GB vision and audio</em></a> | |
| <a class="card" href="https://huggingface.co/Mast-LLM/Gargantua-2.5-Lite"><b>Gargantua Lite Gen 3</b><span>The small one, on Gemma 4 E2B, with vision and audio.</span><em>3.4 GB + 0.99 GB vision and audio</em></a> | |
| <a class="card" href="https://huggingface.co/Mast-LLM/Gargantua-Pro"><b>Gargantua Pro Gen 1</b><span>Our largest model, on Gemma 4 12B.</span><em>7.4 GB</em></a> | |
| <a class="card" href="https://huggingface.co/Mast-LLM/Gargantua-Code-Gen2"><b>Gargantua Code Gen 2</b><span>Writes, fixes and runs code, on Qwen2.5-Coder 7B.</span><em>4.7 GB</em></a> | |
| <a class="card" href="https://huggingface.co/Mast-LLM/Gargantua-Pi"><b>Gargantua Pi Gen 1</b><span>For small boards like the Raspberry Pi and the Orange Pi, in openTARS Pi.</span><em>0.3 GB</em></a> | |
| <a class="card" href="https://huggingface.co/Mast-LLM/Murph"><b>Murph</b><span>A tiny request classifier that picks the kind of task in 0.2 ms, with no GPU.</span><em>4 MB</em></a> | |
| </div> | |
| <p class="note"><b>Built on Gemma 4:</b> Gargantua 2.5 (E4B) and Gargantua Lite Gen 3 (E2B) power openTARS 5.3, with vision and audio.</p> | |
| <p class="note">The models are GGUF files with SHA-256 checksums. Every model card lists the tests we ran and the known limits. They are our own tests on one machine, not public benchmarks.</p> | |
| <h2>Get openTARS</h2> | |
| <div class="links"> | |
| <a href="https://mastllm.github.io/OpenTARS/">Website and downloads</a> | |
| <a href="https://github.com/MastLLM/OpenTARS">GitHub (MIT)</a> | |
| <a href="https://huggingface.co/Mast-LLM/openTARS">App mirror on Hugging Face</a> | |
| </div> | |
| <footer> | |
| MastLLM, makers of openTARS. The openTARS code is MIT. Each model keeps the license of its base: Gemma 4 (Apache-2.0), Qwen2.5-Coder (Apache-2.0) and FunctionGemma (Gemma terms). | |
| Contact: <a class="mail" href="mailto:projectopentars@gmail.com">projectopentars@gmail.com</a> | |
| </footer> | |
| </div> | |
| </body> | |
| </html> | |