---
license: other
license_name: qwen
license_link: https://huggingface.co/Qwen/Qwen3-32B/raw/main/LICENSE
library_name: transformers
base_model: maldv/Shisutemu-Masuta-Q3-32B
base_model_relation: quantized
language:
- en
tags:
- chat
- conversational
pipeline_tags:
- text-generation
- conversational
- chat
---
### exl3 quant
---
### check revisions for quants
---


![image/png](/static-proxy?url=https%3A%2F%2Fcdn-uploads.huggingface.co%2Fproduction%2Fuploads%2F65b19c1b098c85365af5a83e%2FddlwoYb6RjtWkUq1aAS7D.png)

[GGUF](https://huggingface.co/mradermacher/Shisutemu-Masuta-Q3-32B-GGUF) [iMat](https://huggingface.co/mradermacher/Shisutemu-Masuta-Q3-32B-i1-GGUF)

# Shisutemu Masuta Q3 32B

Shisutemu Masuta is a *normalized denoised fourier interpolation* of the following models:

```yaml
output_base_model: "Qwen/Qwen3-32B"
output_dtype: "bfloat16"
finetune_merge:
  - { "model": "Skywork/MindLink-32B-0801", "base": "Qwen/Qwen3-32B", "alpha": 0.8 }
  - { "model": "MetaStoneTec/XBai-o4", "base": "Qwen/Qwen3-32B", "alpha": 0.9, "is_input": true }
  - { "model": "miromind-ai/MiroThinker-32B-SFT-v0.1", "base": "Qwen/Qwen3-32B", "alpha": 0.7 }
  - { "model": "agentica-org/DeepSWE-Preview", "base": "Qwen/Qwen3-32B", "alpha": 0.6 }
  - { "model": "qihoo360/Light-IF-32B", "base": "Qwen/Qwen3-32B", "alpha": 0.6 }
  - { "model": "Jinx-org/Jinx-Qwen3-32B", "base": "Qwen/Qwen3-32B", "alpha": 0.8, "is_output": true }
  - { "model": "Zhihu-ai/Zhi-Create-Qwen3-32B", "base": "Qwen/Qwen3-32B", "alpha": 0.7 }
  - { "model": "DMindAI/DMind-1", "base": "Qwen/Qwen3-32B", "alpha": 0.5 }
  - { "model": "shuttleai/shuttle-3.5", "base": "Qwen/Qwen3-32B", "alpha": 0.8 }
```

In other words, all of these models get warped and interpolated in signal space, and then jammed back on top of the base model (which in this case was Qwen3-32B); with the XBai-o4 input layer and the Jinx-Qwen3-32B output layer.

## Thinking Model

This model uses `<think></think>` tags to generate a sequence of thoughts before generating the response. It excels at generating code and instruction following on any requested task.

## Task Vectors and Alignment

It is clear from the model responses that the task signals from Jinx-Qwen3-32B were successful at controlling alignment, even when diluted by the signals from so many other models.

## Citation

If you find our work helpful, feel free to give us a cite.

```
@misc{shisutemu-masuta-q3-32b,
    title = {Shisutemu Masuta Q3 32},
    url = {https://huggingface.co/maldv/Shisutemu-Masuta-Q3-32B},
    author = {Praxis Maldevide},
    month = {August},
    year = {2025}
}
```