---
language: en
library_name: mlx
tags:
- mlx
- mtp
- speculative-decoding
- draft-model
base_model:
- google/gemma-4-31B-it
pipeline_tag: image-text-to-text
---
# Gemma-4-31B MTP
See Gemma-4-31B in action: [demonstration videos](https://youtube.com/xcreate)

This draft model contains the **Multi-Token Prediction (MTP)** layers from **[google/gemma-4-31B-it-assistant](https://huggingface.co/google/gemma-4-31B-it-assistant)** for use alongside the [Gemma-4-31B-MLX](https://huggingface.co/models?search=inferencerlabs/gemma-4-31b-mlx) model as a speculative decoder for improved performance.

Q4.5-bit quant typically achieves higher throughput with less RAM usage at no loss in quality in our coding test.

#### Tested on a M3 Ultra 512GB RAM using [Inferencer app v1.11.5](https://inferencer.com)
<table style="border-collapse: collapse; border: none; text-align:left; margin-top:10px; margin-bottom:0px;">
  <tr><td><strong>Without decoder</strong></td><td>~15.7 tokens/s ~34.8 GiB (debug build)</td></tr>
  <tr><td><strong>With decoder</strong></td><td>~34.7 tokens/s ~34.8 GiB (debug build)</td></tr>
</table>

<p style="margin-bottom:0;padding-bottom:0;">Enable speculative decoding in Inference Contols:</p>
<div style="margin-left:10px;">
  <img 
    src="https://cdn-uploads.huggingface.co/production/uploads/688479d616f1ec82fa645019/weJgx7wZI7VgOdQe827yS.jpeg"
    style="display:block;margin:0;">
</div>

## 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.