MiniMax-M2.1-GGUF

I am currently looking for open positions! 🤗 If you find this model useful or are looking for a talented AI/LLM Engineer, please reach out to me on LinkedIn: Aaryan Kapoor.

Description

This repository contains GGUF format model files for MiniMaxAI's MiniMax-M2.1.

MiniMax-M2.1 is a state-of-the-art agentic model optimized for coding, tool use, and long-horizon planning. It demonstrates exceptional performance on benchmarks like SWE-bench Verified and VIBE, outperforming or matching models like Claude Sonnet 4.5 in multilingual coding tasks.

About GGUF

GGUF is a new format introduced by the llama.cpp team. It is a replacement for GGML, which is no longer supported by llama.cpp.

How to Run (llama.cpp)

Recommended Parameters: The original developers recommend the following settings for best performance:

• Temperature: 1.0
• Top-P: 0.95
• Top-K: 40

CLI Example

./llama-cli -m MiniMax-M2.1.Q4_K_M.gguf \
  -c 8192 \
  --temp 1.0 \
  --top-p 0.95 \
  --top-k 40 \
  -p "You are a helpful assistant. Your name is MiniMax-M2.1 and is built by MiniMax.\n\nUser: Write a Python script to analyze a CSV file.\nAssistant:" \
  -cnv