ArtusDev
/

nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3

+---
+base_model: nvidia/Qwen-3-Nemotron-32B-GenRM-Principle
+base_model_relation: quantized
+quantized_by: ArtusDev
+---
+<style>
+  .container-dark {
+    font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, "Helvetica Neue", Arial, sans-serif;
+    line-height: 1.6;
+    color: #d4d4d4;
+  }
+  a {
+    color: #569cd6;
+    text-decoration: none;
+    font-weight: 600;
+  }
+  a:hover {
+    text-decoration: underline;
+  }
+  .card-dark {
+    background-color: #252526;
+    border-radius: 12px;
+    padding: 24px;
+    margin-bottom: 20px;
+    box-shadow: 0 4px 12px rgba(0,0,0,0.3);
+    border: 1px solid #3c3c3c;
+  }
+  .card-dark h1 {
+    font-size: 2.2em;
+    color: #ffffff;
+    text-align: center;
+    margin-bottom: 10px;
+  }
+  .card-dark.card-dark-title h1 {
+    font-size: 1.5em;
+  }
+  .card-dark .subtitle {
+    text-align: center;
+    font-size: 1.1em;
+    color: #a0a0a0;
+  }
+  .card-dark h2 {
+    font-size: 1.5em;
+    margin-top: 0;
+    padding-bottom: 10px;
+    border-bottom: 1px solid #3c3c3c;
+    color: #c586c0;
+  }
+  .card-dark h3 {
+    font-size: 1.2em;
+    color: #d4d4d4;
+  }
+  .styled-table {
+    display: table;
+    border: none;
+    width: 100%;
+    font-size: 0.95em;
+    margin-bottom: 0px;
+  }
+  .styled-table thead th {
+    background-color: #333333;
+    color: #c586c0;
+    text-align: left;
+  }
+  .styled-table th {
+    padding: 12px 15px;
+  }
+  .styled-table td {
+    padding: 0;
+  }
+  .styled-table table, .styled-table th, .styled-table td {
+    border-left: none;
+    border-right: none;
+    border-bottom: none;
+  }
+  .styled-table td {
+    border-bottom: 1px solid #3c3c3c;
+  }
+  .styled-table tbody tr {
+    transition: background-color 0.1s ease;
+  }
+  .styled-table tbody tr:hover {
+    background-color: #3a3a3a;
+  }
+  .styled-table tr:last-child td {
+    border-bottom: none;
+  }
+  .styled-table td a {
+    display: block;
+    padding: 12px 15px;
+  }
+  .styled-table td a.fake-link {
+    text-decoration:none;
+    color:inherit;
+  }
+  details {
+    margin-top: 20px;
+    border: 1px solid #3c3c3c;
+    border-radius: 8px;
+    overflow: hidden;
+  }
+  summary {
+    cursor: pointer;
+    padding: 12px 18px;
+    background-color: #6A5ACD;
+    font-weight: 600;
+    display: flex;
+    align-items: center;
+    gap: 10px;
+    justify-content: space-between;
+    list-style: none;
+  }
+  summary::-webkit-details-marker {
+    display: none;
+  }
+  summary:hover {
+    filter: brightness(1.1);
+  }
+  summary::after {
+    content: '';
+    display: inline-block;
+    width: 8px;
+    height: 8px;
+    border-bottom: 2px solid white;
+    border-right: 2px solid white;
+    transform: rotate(45deg);
+    transition: transform 0.3s ease;
+  }
+  details[open] > summary::after {
+    transform: rotate(225deg);
+  }
+  .details-content {
+    padding: 18px;
+  }
+  .btn-purple {
+    display: inline-block;
+    background-color: #6A5ACD;
+    color: white !important;
+    padding: 12px 24px;
+    border-radius: 8px;
+    text-decoration: none;
+    font-weight: 600;
+    transition: background-color 0.3s ease, transform 0.2s ease;
+    text-align: center;
+  }
+  .btn-purple:hover {
+    background-color: #7B68EE;
+    transform: translateY(-2px);
+  }
+</style>
+<div class="container-dark">
+  <div class="card-dark card-dark-title">
+    <h1>ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3</h1>
+    <p class="subtitle">
+      EXL3 quants of <a href="https://huggingface.co/nvidia/Qwen-3-Nemotron-32B-GenRM-Principle" target="_blank">nvidia/Qwen-3-Nemotron-32B-GenRM-Principle</a> using <a href="https://github.com/turboderp-org/exllamav3/" target="_blank">exllamav3</a> for quantization.
+    </p>
+  </div>
+  <div class="card-dark">
+    <h2>Quants</h2>
+    <table class="styled-table">
+      <thead>
+        <tr>
+          <th>Quant</th>
+          <th>BPW</th>
+          <th>Head Bits</th>
+          <th>Size (GB)</th>
+        </tr>
+      </thead>
+      <tbody>
+        <tr>
+          <td><a href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/2.5bpw_H6" target="_blank">2.5_H6</a></td>
+          <td><a class="fake-link" href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/2.5bpw_H6" target="_blank">2.5</a></td>
+          <td><a class="fake-link" href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/2.5bpw_H6" target="_blank">6</a></td>
+          <td><a class="fake-link" href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/2.5bpw_H6" target="_blank">11.93</a></td>
+        </tr>
+        <tr>
+          <td><a href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/3.0bpw_H6" target="_blank">3.0_H6</a></td>
+          <td><a class="fake-link" href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/3.0bpw_H6" target="_blank">3.0</a></td>
+          <td><a class="fake-link" href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/3.0bpw_H6" target="_blank">6</a></td>
+          <td><a class="fake-link" href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/3.0bpw_H6" target="_blank">13.88</a></td>
+        </tr>
+        <tr>
+          <td><a href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/3.5bpw_H6" target="_blank">3.5_H6</a></td>
+          <td><a class="fake-link" href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/3.5bpw_H6" target="_blank">3.5</a></td>
+          <td><a class="fake-link" href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/3.5bpw_H6" target="_blank">6</a></td>
+          <td><a class="fake-link" href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/3.5bpw_H6" target="_blank">15.83</a></td>
+        </tr>
+        <tr>
+          <td><a href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/4.0bpw_H6" target="_blank">4.0_H6</a></td>
+          <td><a class="fake-link" href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/4.0bpw_H6" target="_blank">4.0</a></td>
+          <td><a class="fake-link" href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/4.0bpw_H6" target="_blank">6</a></td>
+          <td><a class="fake-link" href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/4.0bpw_H6" target="_blank">17.78</a></td>
+        </tr>
+        <tr>
+          <td><a href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/4.5bpw_H6" target="_blank">4.5_H6</a></td>
+          <td><a class="fake-link" href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/4.5bpw_H6" target="_blank">4.5</a></td>
+          <td><a class="fake-link" href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/4.5bpw_H6" target="_blank">6</a></td>
+          <td><a class="fake-link" href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/4.5bpw_H6" target="_blank">19.73</a></td>
+        </tr>
+        <tr>
+          <td><a href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/5.0bpw_H6" target="_blank">5.0_H6</a></td>
+          <td><a class="fake-link" href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/5.0bpw_H6" target="_blank">5.0</a></td>
+          <td><a class="fake-link" href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/5.0bpw_H6" target="_blank">6</a></td>
+          <td><a class="fake-link" href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/5.0bpw_H6" target="_blank">21.68</a></td>
+        </tr>
+        <tr>
+          <td><a href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/6.0bpw_H6" target="_blank">6.0_H6</a></td>
+          <td><a class="fake-link" href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/6.0bpw_H6" target="_blank">6.0</a></td>
+          <td><a class="fake-link" href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/6.0bpw_H6" target="_blank">6</a></td>
+          <td><a class="fake-link" href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/6.0bpw_H6" target="_blank">25.58</a></td>
+        </tr>
+        <tr>
+          <td><a href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/8.0bpw_H8" target="_blank">8.0_H8</a></td>
+          <td><a class="fake-link" href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/8.0bpw_H8" target="_blank">8.0</a></td>
+          <td><a class="fake-link" href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/8.0bpw_H8" target="_blank">8</a></td>
+          <td><a class="fake-link" href="https://huggingface.co/ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3/tree/8.0bpw_H8" target="_blank">33.57</a></td>
+        </tr>
+      </tbody>
+    </table>
+  </div>
+  <div class="card-dark">
+    <h2>How to Download and Use Quants</h2>
+    <p>You can download quants by targeting specific size using the Hugging Face CLI.</p>
+    <details>
+      <summary>Click for download commands</summary>
+      <div class="details-content">
+        <b>1. Install huggingface-cli:</b>
+         <pre><code>pip install -U "huggingface_hub[cli]"</code></pre>
+        <b>2. Download a specific quant:</b>
+         <pre><code>huggingface-cli download ArtusDev/nvidia_Qwen-3-Nemotron-32B-GenRM-Principle-EXL3 --revision "5.0bpw_H6" --local-dir ./</code></pre>
+      </div>
+    </details>
+    <p>EXL3 quants can be run with any inference client that supports EXL3, such as <a href="https://github.com/theroyallab/tabbyapi" target="_blank"><b>TabbyAPI</b></a>. Refer to <a href="https://github.com/theroyallab/tabbyAPI/wiki/01.-Getting-Started" target="_blank">documentation</a> for set up instructions.</p>
+  </div>
+  <div class="card-dark">
+    <h2>Quant Requests</h2>
+    <div style="text-align: center; margin-top: 25px;">
+      <a href="https://huggingface.co/ArtusDev/requests-exl/discussions/new?title=[MODEL_NAME_HERE]&description=[MODEL_HF_LINK_HERE]" class="btn-purple" target="_blank">Request EXL3 Quants</a>
+    </div>
+    <p class="subtitle">
+      See <a href="https://huggingface.co/ArtusDev/requests-exl" target="_blank">EXL community hub</a> for request guidelines.
+    </p>
+  </div>
+</div>