---
datasets:
- PowerInfer/QWQ-LONGCOT-500K
- PowerInfer/LONGCOT-Refine-500K
base_model:
- Qwen/Qwen2.5-3B-Instruct
pipeline_tag: text-generation
language:
- en
library_name: transformers
tags:
- llama-cpp
- imatrix
- gguf
- IQ4_XS
- 3b
- SmallThinker
- qwen
- llama-cpp
- PowerInfer
- code
- math
- chat
- roleplay
- text-generation
- safetensors
- nlp
- code
---

# roleplaiapp/SmallThinker-3B-Preview-IQ4_XS-GGUF

**Repo:** `roleplaiapp/SmallThinker-3B-Preview-IQ4_XS-GGUF`  
**Original Model:** `SmallThinker-3B-Preview`
**Organization:** `PowerInfer`
**Quantized File:** `smallthinker-3b-preview-iq4_xs-imat.gguf`
**Quantization:** `GGUF`
**Quantization Method:** `IQ4_XS`  
**Use Imatrix:** `True`  
**Split Model:** `False`

## Overview
This is an imatrix GGUF IQ4_XS quantized version of [SmallThinker-3B-Preview](https://huggingface.co/PowerInfer/SmallThinker-3B-Preview).

## Quantization By
I often have idle A100 GPUs while building/testing and training the RP app, so I put them to use quantizing models.
I hope the community finds these quantizations useful.

Andrew Webby @ [RolePlai](https://roleplai.app/)