This is a MXFP4 quantization of Qwen3-Coder-Next-REAM

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

GGUF

Model size

60B params

Architecture

qwen3next

Hardware compatibility

4-bit

Model tree for noctrex/Qwen3-Coder-Next-REAM-MXFP4_MOE-GGUF

Base model

Finetuned

Quantized

(5)

this model