---
title: Intern-S2-Preview-397B-MLX-Q9-archive
canonical_url: "https://www.modelscope.ai/models/inferencerlabs/Intern-S2-Preview-397B-MLX-Q9-archive"
md_url: "https://www.modelscope.ai/models/inferencerlabs/Intern-S2-Preview-397B-MLX-Q9-archive.md"
repository: inferencerlabs/Intern-S2-Preview-397B-MLX-Q9-archive
last_updated: 2026-07-31
license: apache-2.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - qwen3_5_moe
architectures:
  - InternS2PreviewForConditionalGeneration
base_model:
  - internlm/Intern-S2-Preview-397B
base_model_relation: quantized
parameters: 124.3B
tensor_type:
  - U32
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 19
stars: 0
tags:
  - mlx
  - quantized
---

# Intern-S2-Preview-397B-MLX-Q9-archive

> Intern-S2-Preview-397B-MLX-Q9-archive - An open-source model by inferencerlabs on ModelScope. Intern-S2-Preview-397B See Intern-S2-Preview-397B in action: demonstration videos Tested with an M3 Ultra 512 GiB using Inferencer app v2.2.2 Text Inference: 25.3…

inferencerlabs/Intern-S2-Preview-397B-MLX-Q9-archive is a 124.3B-parameter image-text-to-text model on ModelScope. licensed under apache-2.0. derived from internlm/Intern-S2-Preview-397B.

- **Repository**: inferencerlabs/Intern-S2-Preview-397B-MLX-Q9-archive
- **License**: apache-2.0
- **Tasks**: image-text-to-text
- **Parameters**: 124.3B
- **Base model**: internlm/Intern-S2-Preview-397B
- **Tags**: mlx, quantized
- **Downloads**: 19
- **Stars**: 0
- **Last updated**: 2026-07-31

Source: https://www.modelscope.ai/models/inferencerlabs/Intern-S2-Preview-397B-MLX-Q9-archive

---

# Intern-S2-Preview-397B
See Intern-S2-Preview-397B in action: [demonstration videos](https://youtube.com/xcreate)
   
#### Tested with an M3 Ultra 512 GiB using [Inferencer app v2.2.2](https://inferencer.com)
- Text Inference: ~25.3 tokens/s @ 1000 tokens ~415.4 GiB
- Vision Inference: ~23.4 tokens/s ~416.2 GiB

<p style="margin-bottom:0px;">
<strong>Q9 typically achieves near lossless accuracy</strong>

![Screenshot](https://cdn-uploads.huggingface.co/production/uploads/688479d616f1ec82fa645019/jvHXVsv1NcWPeOBWD1ewu.jpeg)
</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>q4.5</strong></td><td>1.32812</td><td>90.5%</td><td>26.44%</td></tr>
<tr><td><strong>q5.5</strong></td><td>1.23437</td><td>95.4%</td><td>16.03%</td></tr>
<tr><td><strong>q6.5</strong></td><td>1.21875</td><td>96.85%</td><td>12.55%</td></tr>
<tr><td><strong>q8.5</strong></td><td>1.21875</td><td>97.65%</td><td>9.92%</td></tr>
<tr><td><strong>q9</strong></td><td>1.21093</td><td>97.95%</td><td>9.61%</td></tr>
<tr><td><strong>Base</strong></td><td>1.20312</td><td>100.0%</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 [internlm/Intern-S2-Preview-397B](https://huggingface.co/internlm/Intern-S2-Preview-397B).

## 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.