Those of you running minimax 2.7 locally, how are you feeling about it?
Im running the raw version straight from the minimax release on hugging face (https://huggingface.co/MiniMaxAI/MiniMax-M2.7) on 3 rtx pro 6000's on vllm. So no quantization.
Im running the raw version straight from the minimax release on hugging face (https://huggingface.co/MiniMaxAI/MiniMax-M2.7) on 3 rtx pro 6000's on vllm. So no quantization.