MiniMaxAI/M1 models
#1070
by piloponth - opened
It really baffles me why there aren’t any quantizations, so iI try…
kindly asking for quants for
piloponth changed discussion title from MiniMaxAI/M1 model to MiniMaxAI/M1 models
The MiniMaxM1ForCausalLM architecture is unfortunately not currently supported by llama.cpp which is a requirement for GGUF quants to be possible. This is really unfortunate as I would love to try out this massive 456B model.
Thank you for the clarification of the situation.
Best, Pilo.
piloponth changed discussion status to closed