antirez: DwarfStar Runs DeepSeek v4 Flash and GLM 5.2 Tensor Parallel on Two MacBooks via RDMA

antirez · x · 2026-07-07

Redis creator antirez announces that on DwarfStar, using RDMA, tensor parallelism was achieved on two M5Max 128GB MacBooks, successfully running DeepSeek v4 Flash and GLM 5.2.

Particularly significant for GLM: previously no single commercially available machine could fully fit the model in GPU memory, now cross-machine tensor parallelism enables it, an engineering breakthrough for local/edge deployment of frontier open-source models.

Original post →

More from Infra

Infra channel →