DeepSeek V4.1 Flash runs locally on 128GB Strix Halo via SSD streaming or two-node TCP/RoCE

antirez · x · 2026-09-23

Developer dcapitella added support for DeepSeek V4.1 Flash in antirez's DwarfStar local inference tool, running it on AMD Strix Halo (128GB unified memory) and testing two deployment paths: SSD streaming on a single 128GB machine, or distributing the model across two nodes over TCP or RoCE networking. A concrete demonstration of running large models off the data center on workstation-class hardware.

Original post →

More from Infra

Infra channel →