Minimax M3 sm_120
Summary
Minimax's M3 model requires vllm updates to support sm_120 compute capability, as the current repo only supports sm_100.
Similar Articles
Minimiax M3 releasing with some new things
Minimax is releasing its new M3 model with unspecified new features.
Minimax M3 support with MSA has been merged into llama.cpp
Minimax M3 support with MSA has been merged into llama.cpp, enabling inference for the Minimax M3 model using the MSA architecture.
@TeksEdge: With MiniMax M3 open source now out, here is what to expect on quants and sizes, including VRAM needed: MiniMax M3 (428…
MiniMax M3, a 428B MoE model with ~23B active parameters, is now open source. It offers ultra-long context (up to 1M) and efficiency improvements, with various quantized sizes and VRAM requirements for local deployment.
Minimax M3 vs M2.7
Discussion comparing the new Minimax M3 model to its predecessor M2.7, seeking user feedback after two weeks of release.
Vision Support for Minimax-M3 has been merged into llama.cpp
Vision support for the Minimax-M3 model has been merged into the llama.cpp project, enabling multimodal inference for this model locally.