name: MiniMax-M2.5-REAP-139B-A10B-GGUF-MXFP4_MOE
base_model: MiniMaxAI/MiniMax-M2.5
license: other
pipeline_tag: text-generation
tasks: text-generation
language: en
library_name: llama.cpp
tags:
- Cerebras
- MiniMaxAI
- M2.5
- REAP
- GGUF
- static quantization
- MXFP4

Description

Its a single file merge of a sharded MiniMax-M2.5-REAP-139B-A10B-GGUF-MXFP4_MOE compatible with ollama.

MiniMax-M2.5-REAP-139B-A10B is a 230 billion parameter MiniMax M2.5 model with 40% of its experts pruned with REAP (Router-weighted Expert Activation Pruning). This model is converted to GGUF and quantized to MXFP4.

exdysa/MiniMax-M2.5-REAP-139B-A10B-GGUF-MXFP4_MOE

Description

exdysa/
MiniMax-M2.5-REAP-139B-A10B-GGUF-MXFP4_MOE