noctrex
/

SmallThinker-21B-A3B-Instruct-MXFP4_MOE-GGUF

Text Generation

Model card Files Files and versions

This is a MXFP4_MOE quantization of the model SmallThinker-21BA3B-Instruct

Original model: https://huggingface.co/PowerInfer/SmallThinker-21BA3B-Instruct

Downloads last month: 403

GGUF

Model size

22B params

Architecture

smallthinker

Hardware compatibility

Log In to view the estimation

4-bit

Model tree for noctrex/SmallThinker-21B-A3B-Instruct-MXFP4_MOE-GGUF

Base model

PowerInfer/SmallThinker-21BA3B-Instruct

Quantized

(4)

this model