---
title: GLM-5.3-MLX-Q4i
canonical_url: "https://www.modelscope.cn/models/inferencerlabs/GLM-5.3-MLX-Q4i"
md_url: "https://www.modelscope.cn/models/inferencerlabs/GLM-5.3-MLX-Q4i.md"
repository: inferencerlabs/GLM-5.3-MLX-Q4i
last_updated: 2026-11-08
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - glm_moe_dsa
architectures:
  - GlmMoeDsaForCausalLM
base_model:
  - zai-org/GLM-5.3-BF16
base_model_relation: quantized
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 65
stars: 0
tags:
  - quantized
  - mlx
---

# GLM-5.3-MLX-Q4i

> GLM-5.3-MLX-Q4i - inferencerlabs 在 ModelScope 开源的模型。See GLM 5.3 in action: demonstration videos

inferencerlabs/GLM-5.3-MLX-Q4i 是 ModelScope 魔搭社区上的text-generation模型，基于 zai-org/GLM-5.3-BF16 构建。

- **Repository**: inferencerlabs/GLM-5.3-MLX-Q4i
- **Tasks**: text-generation
- **Base model**: zai-org/GLM-5.3-BF16
- **Tags**: quantized, mlx
- **Downloads**: 65
- **Stars**: 0
- **Last updated**: 2026-11-08

Source: https://www.modelscope.cn/models/inferencerlabs/GLM-5.3-MLX-Q4i

---

# GLM 5.3

See GLM 5.3 in action: [demonstration videos](https://youtube.com/xcreate)

For improved performance, download and enable a compatible [MTP speculative decoder](https://huggingface.co/models?search=inferencerlabs/glm-5.3-mtp-mlx).
   
#### Tested with a M3 Ultra using [Inferencer app](https://inferencer.com)
- Text Inference: ~15.8 tokens/s @ 1000 tokens ~428.6 GiB

![Screenshot 1](https://cdn-uploads.huggingface.co/production/uploads/688479d616f1ec82fa645019/EWwAwH0SaGInwfy2VpaiF.jpeg)
![Screenshot 2](https://cdn-uploads.huggingface.co/production/uploads/688479d616f1ec82fa645019/ItV8dQvT85bsz-m98IBOT.jpeg)
![Screenshot 3](https://cdn-uploads.huggingface.co/production/uploads/688479d616f1ec82fa645019/cltc2PcH2XELw_hZGx24H.jpeg)
![Screenshot 4](https://cdn-uploads.huggingface.co/production/uploads/688479d616f1ec82fa645019/IGCOL6C_C-Mzw6IoXWNkt.jpeg)

<p style="margin-bottom:0px;">
<strong>Q4-INF uses the data-agnostic INF method tuned to yield maximum general accuracy within a 512 GiB memory budget.</strong>

Due to system memory and time constraints, the figures shown below are from the conversion of GLM 5.1.
</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</strong></td><td>1.35937</td><td>89.75%</td><td>28.98%</td></tr>
<tr><td><strong>Q4-INF</strong></td><td>1.21093</td><td>97.70%</td><td>10.65%</td></tr>
<tr><td><strong>Q5</strong></td><td>1.24218</td><td>94.60%</td><td>17.55%</td></tr>
<tr><td><strong>Q6</strong></td><td>1.21875</td><td>96.85%</td><td>16.03%</td></tr>
<tr><td><strong>Q8</strong></td><td>1.21875</td><td>97.65%</td><td>9.92%</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 [zai-org/GLM-5.3](https://huggingface.co/zai-org/GLM-5.3).

## 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.