runfuture/MiniMax-M2.1-REAP-50-W4A16-GGUF

MiniMax-M2.1-REAP-50-W4A16 (GGUF Q4_0)

This repository hosts a GGUF conversion of 0xSero/MiniMax-M2.1-REAP-50-W4A16 using legacy Q4_0 quantization for llama.cpp-compatible runtimes.

Files

• 0xSero-MiniMax-M2.1-REAP-50-W4A16-Q4_0.gguf

Usage (llama.cpp)

./main -m 0xSero-MiniMax-M2.1-REAP-50-W4A16-Q4_0.gguf -p "Hello"

Conversion

Converted locally with a Python CLI that wraps llama.cpp's convert_hf_to_gguf.py and emits legacy Q4_0.

License

Please refer to the original model repository for licensing and usage terms: https://huggingface.co/MiniMaxAI/MiniMax-M2.1 https://huggingface.co/0xSero/MiniMax-M2.1-REAP-50-W4A16