---
language: en
tags:
- quantized
- mlx
base_model:
- inclusionAI/Ring-2.6-1T
base_model_relation: quantized
library_name: mlx
pipeline_tag: text-generation
---
**See Ring-2.6-1T in action - [demonstration videos](https://youtube.com/xcreate)**
   
#### Tested with an M3 Ultra 512 GiB using [Inferencer app](https://inferencer.com)
- Text inference: ~11.5 tokens/s @ 1000 tokens ~440 GiB (debug build)

<p style="margin-bottom:0px;">
<strong>Q3.7-INF uses the data-agnostic INF method tuned to yield maximum general accuracy within a 512 GiB memory budget</strong>

![Screenshot](https://cdn-uploads.huggingface.co/production/uploads/688479d616f1ec82fa645019/HgGe753iCnfujJac9Xfce.jpeg)

The perplexity of this quantization has not been directly compared against the base model due to resource and time constraints. For general guidance, the evaluations below reference a similarly sized model (Kimi K2.6). However, please note that Kimi K2.6 uses quantization-aware training (QAT), so these results are not directly comparable and should be treated as context only.
</p>
<table style="border-collapse: collapse; text-align:center; margin-top:10px; margin-bottom:0px;">
<thead>
<tr><th>Quantization (bpw)</th><th>Perplexity</th><th>Token Accuracy</th><th>Missed Divergence</th></tr>
</thead>
<tbody>
<tr><td><strong>Q3.5</strong></td><td>1.1328125</td><td>94.92%</td><td>42.71%</td></tr>
<tr><td><strong>Q3.5-INF</strong></td><td>1.078125</td><td>96.67%</td><td>22.04%</td></tr>
<tr><td><strong>Q3.6</strong></td><td>1.1484375</td><td>94.72%</td><td>48.72%</td></tr>
<tr><td><strong>Q4.2-INF</strong></td><td>1.0546875</td><td>99.02%</td><td>13.73%</td></tr>
<tr><td><strong>Base</strong></td><td>Untested</td><td>100%</td><td>0.000%</td></tr>
</tbody>
</table>

<ul>
<li style="margin:0;">Perplexity: Measures the confidence for predicting base tokens (lower is better)</li>
<li style="margin:0;">Token Accuracy: The percentage of correctly generated base tokens</li>
<li style="margin:0;">Missed Divergence: Measures severity of misses; how much the token was missed by</li>
</ul>

##### Quantized with a modified version of [MLX](https://github.com/ml-explore/mlx)
##### For more details see our [demonstration videos](https://youtube.com/xcreate) or visit [Ring-2.6-1T](https://huggingface.co/inclusionAI/Ring-2.6-1T).

## Disclaimer

We are not the creator, originator, or owner of any model listed. Each model is created and provided by third parties. Models may not always be accurate or contextually appropriate. You are responsible for verifying the information before making important decisions. We are not liable for any damages, losses, or issues arising from its use, including data loss or inaccuracies in AI-generated content.