MiniMaxAI__MiniMax-M3-RTN-int4-sym-g128-faked-bf16 is an open-source, quantized language model designed for efficient local inference. It is suitable for researchers and developers who need to run large models on limited hardware, with open weights and CLI deployment.
MiniMaxAI MiniMax M3 RTN Int4 Sym G128 Faked is a Foundation models & chat product. It focuses on enabling efficient local inference of large language models through quantized open-source weights. It is built as an open-source project for AI researchers and developers. MiniMaxAI MiniMax M3 RTN Int4 Sym G128 Faked is open source under the Open Source license. MiniMaxAI MiniMax M3 RTN Int4 Sym G128 Faked is available on the command line, and it can be self-hosted.
Behind MiniMaxAI MiniMax M3 RTN Int4 Sym G128 Faked is meteorain, and the product first shipped in 2026. Development happens publicly on GitHub with 397 stars and 12 commits in the last 90 days. PulseGate's similarity index finds few close equivalents — MiniMaxAI MiniMax M3 RTN Int4 Sym G128 Faked occupies a relatively distinct niche. Key capabilities include text generation, quantized weights, and efficient inference.
Latest indexed changes and source events
meteorain/MiniMaxAI__MiniMax-M3-RTN-int4-sym-g128-faked-bf16 discovered by the PulseGate indexer
Other apps tracked under the same category.
