This is a MXFP4 quantization of Mattepiu/Qwen3-Coder-Next-REAP-48B-A3B

Use the following sampling parameters as suggested:
temperature=1.0
top_p=0.95
top_k=40

Downloads last month
415
GGUF
Model size
49B params
Architecture
qwen3next
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for noctrex/Qwen3-Coder-Next-REAP-48B-A3B-MXFP4_MOE-GGUF

Quantized
(3)
this model