Spaces:
Running
Running
Open external links in a new tab (GitHub and others refuse to load inside the Space frame)
b9f9541 verified | <html lang="en"> | |
| <head> | |
| <meta charset="utf-8"> | |
| <meta name="viewport" content="width=device-width, initial-scale=1"> | |
| <title>Genrius AI</title> | |
| <style> | |
| body { margin: 0; background: #0b0b0c; color: #e8e6e1; font-family: system-ui, -apple-system, Segoe UI, Roboto, sans-serif; line-height: 1.55; } | |
| main { max-width: 760px; margin: 0 auto; padding: 40px 16px; } | |
| h1 { color: #D4AF37; margin: 0 0 4px; font-size: 2rem; } | |
| .tag { color: #b9b4a8; margin: 0 0 28px; } | |
| h2 { color: #D4AF37; font-size: 1.15rem; margin-top: 28px; } | |
| a { color: #D4AF37; } | |
| img { width: 100%; height: auto; border-radius: 8px; margin: 16px 0; } | |
| li { margin: 6px 0; } | |
| </style> | |
| </head> | |
| <body> | |
| <main> | |
| <h1>Genrius AI</h1> | |
| <p class="tag">Generating Real Intelligence. We build AI models and make them small and fast enough to run on hardware people already own.</p> | |
| <h2>Pingala-8: 2-bit LLMs for llama.cpp, no retraining</h2> | |
| <ul> | |
| <li>85% smaller: Qwen3-4B goes from 8.05 GB to 1.24 GB, and Llama 3.1 8B from 16.08 GB to 2.39 GB.</li> | |
| <li>At the file size of llama.cpp's IQ2_XXS, our Qwen3-4B reaches WikiText-2 perplexity 16.64. IQ2_XXS reaches 28.61 and the best IQ2_KT file we built reaches 18.15 (lower is better).</li> | |
| <li>Where we lose: Qwen3-14B (IQ2_KT 9.40, ours 9.57), prompt processing (0.74x of IQ2_XXS), and retrained models such as Ternary Bonsai 4B.</li> | |
| </ul> | |
| <img src="pingala8-poster.jpg" alt="Pingala-8 Qwen3-4B (1.24 GB) answering in a local chat window on an RTX 5070 Ti Laptop GPU"> | |
| <h2>Links</h2> | |
| <ul> | |
| <li><a href="https://github.com/Genrius-AI/pingala8-llm/releases/tag/v2.4-oneclick" target="_blank" rel="noopener noreferrer">One-click Windows build</a></li> | |
| <li><a href="https://github.com/Genrius-AI/pingala8-llm" target="_blank" rel="noopener noreferrer">Code</a></li> | |
| <li><a href="https://doi.org/10.5281/zenodo.23481757" target="_blank" rel="noopener noreferrer">Paper</a></li> | |
| <li><a href="https://huggingface.co/Genrius-AI/Qwen3-4B-Pingala8-2bit" target="_blank" rel="noopener noreferrer">Qwen3-4B-Pingala8-2bit</a> and <a href="https://huggingface.co/Genrius-AI/Llama-3.1-8B-Pingala8-2bit" target="_blank" rel="noopener noreferrer">Llama-3.1-8B-Pingala8-2bit</a></li> | |
| <li><a href="https://huggingface.co/datasets/Genrius-AI/pingala8-benchmarks" target="_blank" rel="noopener noreferrer">Benchmark tables</a></li> | |
| </ul> | |
| </main> | |
| <script>document.addEventListener("click",function(e){var a=e.target.closest&&e.target.closest('a[href^="http"]');if(a){a.target="_blank";a.rel="noopener noreferrer";}},true);</script> | |
| </body> | |
| </html> | |