Add Qwen3.5-2B and Qwen3.5-0.8B Pingala-8 to the models table

README.md

@@ -19,8 +19,10 @@ Founded by Harshit Goyal, former Google software engineer and IIIT Delhi alumnus
 | [Qwen3-4B-Pingala8-2bit](https://huggingface.co/Genrius-AI/Qwen3-4B-Pingala8-2bit) | 1.24 GB | 16.64 | 28.61 |
 | [Llama-3.1-8B-Pingala8-2bit](https://huggingface.co/Genrius-AI/Llama-3.1-8B-Pingala8-2bit) | 2.39 GB | 9.14 | 12.35 |
 | [Qwen3.5-4B-Pingala8-2bit](https://huggingface.co/Genrius-AI/Qwen3.5-4B-Pingala8-2bit) | 1.51 GB | 10.97 | 14.75 |
+| [Qwen3.5-2B-Pingala8-2bit](https://huggingface.co/Genrius-AI/Qwen3.5-2B-Pingala8-2bit) | 0.78 GB | 15.62 | 29.08 |
+| [Qwen3.5-0.8B-Pingala8-2bit](https://huggingface.co/Genrius-AI/Qwen3.5-0.8B-Pingala8-2bit) | 0.35 GB | 25.97 | 85.09 |
 
-Lower is better. The files need our patched llama.cpp build (NVIDIA CUDA); stock llama.cpp, Ollama and LM Studio cannot load them.
+Lower is better. The files need our patched llama.cpp build (NVIDIA CUDA); stock llama.cpp, Ollama and LM Studio cannot load them. Qwen3.5-2B and Qwen3.5-0.8B need the rebuilt runtime (the released patch plus a loader patch on main); the one-click build cannot load them yet.
 
 ## Pingala-8: 2-bit LLMs for llama.cpp, no retraining
 

index.html

@@ -27,8 +27,10 @@
     <tr><td><a href="https://huggingface.co/Genrius-AI/Qwen3-4B-Pingala8-2bit" target="_blank" rel="noopener noreferrer">Qwen3-4B-Pingala8-2bit</a></td><td>1.24 GB</td><td>16.64</td><td>28.61</td></tr>
     <tr><td><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></td><td>2.39 GB</td><td>9.14</td><td>12.35</td></tr>
     <tr><td><a href="https://huggingface.co/Genrius-AI/Qwen3.5-4B-Pingala8-2bit" target="_blank" rel="noopener noreferrer">Qwen3.5-4B-Pingala8-2bit</a></td><td>1.51 GB</td><td>10.97</td><td>14.75</td></tr>
+    <tr><td><a href="https://huggingface.co/Genrius-AI/Qwen3.5-2B-Pingala8-2bit" target="_blank" rel="noopener noreferrer">Qwen3.5-2B-Pingala8-2bit</a></td><td>0.78 GB</td><td>15.62</td><td>29.08</td></tr>
+    <tr><td><a href="https://huggingface.co/Genrius-AI/Qwen3.5-0.8B-Pingala8-2bit" target="_blank" rel="noopener noreferrer">Qwen3.5-0.8B-Pingala8-2bit</a></td><td>0.35 GB</td><td>25.97</td><td>85.09</td></tr>
   </table>
-  <p class="lead">Lower is better. The files need our patched llama.cpp build (NVIDIA CUDA); stock llama.cpp, Ollama and LM Studio cannot load them.</p>
+  <p class="lead">Lower is better. The files need our patched llama.cpp build (NVIDIA CUDA); stock llama.cpp, Ollama and LM Studio cannot load them. Qwen3.5-2B and Qwen3.5-0.8B need the rebuilt runtime (the released patch plus a loader patch on main); the one-click build cannot load them yet.</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>
@@ -42,7 +44,7 @@
     <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>, <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> and <a href="https://huggingface.co/Genrius-AI/Qwen3.5-4B-Pingala8-2bit" target="_blank" rel="noopener noreferrer">Qwen3.5-4B-Pingala8-2bit</a> (text only)</li>
+    <li><a href="https://huggingface.co/Genrius-AI/Qwen3-4B-Pingala8-2bit" target="_blank" rel="noopener noreferrer">Qwen3-4B-Pingala8-2bit</a>, <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> and <a href="https://huggingface.co/Genrius-AI/Qwen3.5-4B-Pingala8-2bit" target="_blank" rel="noopener noreferrer">Qwen3.5-4B-Pingala8-2bit</a> (text only); <a href="https://huggingface.co/Genrius-AI/Qwen3.5-2B-Pingala8-2bit" target="_blank" rel="noopener noreferrer">Qwen3.5-2B-Pingala8-2bit</a> and <a href="https://huggingface.co/Genrius-AI/Qwen3.5-0.8B-Pingala8-2bit" target="_blank" rel="noopener noreferrer">Qwen3.5-0.8B-Pingala8-2bit</a> (text only, rebuilt runtime)</li>
     <li><a href="https://huggingface.co/datasets/Genrius-AI/pingala8-benchmarks" target="_blank" rel="noopener noreferrer">Benchmark tables</a></li>
   </ul>
 </main>