marksverdhei/MiniMax-M2.5-GGUF

MiniMax-M2.5 GGUF

GGUF quantizations of MiniMaxAI/MiniMax-M2.5, created with llama.cpp.

Model Details

Property	Value
Base model	MiniMaxAI/MiniMax-M2.5
Architecture	Mixture of Experts (MoE)
Total parameters	230B
Active parameters	10B per token
Layers	62
Total experts	256
Active experts per token	8
Source precision	FP8 (float8_e4m3fn)

Available Quantizations

Quantization	Size	Description
Q8_0	227 GB	8-bit quantization, highest quality
Q4_K_M	129 GB	4-bit K-quant (medium), good balance of quality and size
IQ3_S	92 GB	3-bit importance quantization (small), compact
Q2_K	78 GB	2-bit K-quant, smallest size

Usage

These GGUFs can be used with llama.cpp and compatible frontends.

# Example with llama-cli
llama-cli -m MiniMax-M2.5-Q4_K_M.gguf -p "Hello" -n 128

Notes

• The source model uses FP8 (float8_e4m3fn) precision, so Q8_0 is effectively lossless relative to the source weights.
• This is a large MoE model. Even the smallest quant (Q2_K) requires ~78GB due to the number of experts.
• Quantized from the official MiniMaxAI/MiniMax-M2.5 weights.