This is a MXFP4_MOE quantization of the model Step-3.5-Flash

Downloads last month
514
GGUF
Model size
197B params
Architecture
step35
Hardware compatibility
Log In to add your hardware

4-bit

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

Model tree for noctrex/Step-3.5-Flash-MXFP4_MOE-GGUF

Quantized
(20)
this model