Comment by nl 14 hours ago > You could run it on a cluster of nodesNot sure this is a MBP either. 2 comments nl Reply bigyabai 8 hours ago Not even a cluster of Mac Pros could run a dense 5T parameter model with RDMA, to my knowledge. zozbot234 7 hours ago SOTA models are reportedly MoE, not dense.
bigyabai 8 hours ago Not even a cluster of Mac Pros could run a dense 5T parameter model with RDMA, to my knowledge. zozbot234 7 hours ago SOTA models are reportedly MoE, not dense.
Not even a cluster of Mac Pros could run a dense 5T parameter model with RDMA, to my knowledge.
SOTA models are reportedly MoE, not dense.