---
language: en
library_name: mlx
tags:
- quantized
- mlx
base_model:
- zai-org/GLM-5
pipeline_tag: text-generation
---
# CURRENTLY UPLOADING...
# CURRENTLY UPLOADING...
# CURRENTLY UPLOADING...
**See GLM-5 MLX over in action - [demonstration video](https://youtu.be/3XCYruBYr-0)**

#### Tested across a M3 Ultra 512GB RAM and M4 Max 128GB RAM with [Inferencer v1.10.1 distributed compute](https://inferencer.com)
- Distributed inference ~12.5 tokens/s @ 1000 tokens
- Memory usage: ~444 GB / 49GB

*q5.6bit quant is currently unranked, but should fit above q5.5*
| Quantization | Perplexity | Token Accuracy | Missed Divergence |
|:------------:|:----------:|:--------------:|:-----------------:|
| **q3.5**     | 168.0      | 43.45%         | 72.57%            |
| **q4.5**     | 1.33593    | 91.65%         | 27.61%            |
| **q4.8**     | 1.28125    | 93.75%         | 21.15%            |
| **q5.5**     | 1.23437    | 95.05%         | 17.28%            |
| **q6.5**     | 1.21875    | 96.95%         | 12.03%            |
| **q8.5**     | 1.21093    | 97.55%         | 10.50%            |
| **q9**       | 1.21093    | 97.55%         | 10.50%            |
| **Base**     | 1.20312    | 100.0%         | 0.000%            |

- Perplexity: Measures the confidence for predicting base tokens (lower is better)
- Token Accuracy: The percentage of correctly generated base tokens
- Missed Divergence: Measures severity of misses; how much the token was missed by

##### Quantized with a modified version of [MLX](https://github.com/ml-explore/mlx)
##### For more details see [demonstration video](https://youtu.be/3XCYruBYr-0) or visit [GLM-5](https://huggingface.co/zai-org/GLM-5).

## 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.