ertghiu256
/

qwen-3-4b-mixture-of-thought-gguf

Model card Files Files and versions Community

Model Info:

A small qwen 3 model trained on 34000 data collected from open-r1/mixture-of-thought.

Usage:

Solve math
Generate codes
Thinking

Downloads last month: 33

GGUF

Model size

4.02B params

Architecture

qwen3

Hardware compatibility

Log In to view the estimation

4-bit

5-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ertghiu256/qwen-3-4b-mixture-of-thought-gguf

Base model

Qwen/Qwen3-4B-Base

Finetuned

Quantized

(93)

this model

Datasets used to train ertghiu256/qwen-3-4b-mixture-of-thought-gguf