---
license: apache-2.0
language:
- en
base_model:
- prithivMLmods/Capricornus-MoT-1.7B-Supreme1
pipeline_tag: text-generation
library_name: transformers
tags:
- text-generation-inference
- math
- code
- science
---

# **Capricornus-MoT-1.7B-Supreme1-GGUF**

> **Capricornus-MoT-1.7B-Supreme1** is a **high-precision, multi-domain expert model** fine-tuned from **Qwen3-1.7B**, built for **code generation**, **mathematical reasoning**, **scientific analysis**, and **open technical inference**. Trained on the **Mixture of Thoughts (MoT)** dataset with combined expert clusters in **code, math, and science**, and enhanced with an **Open Code Reasoning** dataset, it delivers powerful symbolic and structured outputs in a wide range of STEM and reasoning domains.

## Model File

| File Name                                        | Size   | Format        | Description                              |
|--------------------------------------------------|--------|---------------|------------------------------------------|
| Capricornus-MoT-1.7B-Supreme1.BF16.gguf         | 3.45 GB| GGUF (BF16)   | BFloat16 precision model file            |
| Capricornus-MoT-1.7B-Supreme1.F16.gguf          | 3.45 GB| GGUF (F16)    | Float16 precision model file             |
| Capricornus-MoT-1.7B-Supreme1.F32.gguf          | 6.89 GB| GGUF (F32)    | Float32 precision model file             |
| Capricornus-MoT-1.7B-Supreme1.Q4_K_M.gguf       | 1.11 GB| GGUF (Q4_K_M) | 4-bit quantized model file               |
| Capricornus-MoT-1.7B-Supreme1.Q5_K_M.gguf       | 1.26 GB| GGUF (Q5_K_M) | 5-bit quantized model file               |
| Capricornus-MoT-1.7B-Supreme1.Q8_0.gguf         | 1.83 GB| GGUF (Q8_0)   | 8-bit quantized model file               |
| config.json                                     | 31 B   | JSON          | Configuration file                       |
| .gitattributes                                  | 1.98 kB| Text          | Git attributes configuration             |

## Quants Usage 

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):

![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)