Business Shanghai's Yuanshi Technology Raises Nearly RMB 300 Million for AI Virtual Cells, Two Weeks After the Last Chinese Record Fell Security GAO Finds No Widely Accepted Test for Generative AI Cyber Skills and Hands Congress 16 Options, Including Human Sign-Off on Consequential Actions News Microsoft Turns Three USB4-Cabled PCs Into One AI Machine: Qwen3-235B Runs at Up to 22 Tokens a Second Across 384GB of Ordinary Memory Business Dell, HPE, Lenovo and Supermicro Are Demanding Up to 45% More for Signed AI Server Deals, and Trading Firms Are Paying Opinion OpenAI Scores Its Own Models on 99 Drug-Chemistry Problems, and Compound Selection Is Where They Stall Coding Assistants AWS Puts Distributed KV Caching Behind an Agent Skill: Up to 40% Cheaper Inference and 80% Faster First Token AI Agents Tencent and King's College London Build an Agent Memory Test From 80,299 Real Group-Chat Messages News Tesla Starts FSD v15 With a Generative Reality View and a 25x Intervention Claim It Has Not Published Business Shanghai's Yuanshi Technology Raises Nearly RMB 300 Million for AI Virtual Cells, Two Weeks After the Last Chinese Record Fell Security GAO Finds No Widely Accepted Test for Generative AI Cyber Skills and Hands Congress 16 Options, Including Human Sign-Off on Consequential Actions News Microsoft Turns Three USB4-Cabled PCs Into One AI Machine: Qwen3-235B Runs at Up to 22 Tokens a Second Across 384GB of Ordinary Memory Business Dell, HPE, Lenovo and Supermicro Are Demanding Up to 45% More for Signed AI Server Deals, and Trading Firms Are Paying Opinion OpenAI Scores Its Own Models on 99 Drug-Chemistry Problems, and Compound Selection Is Where They Stall Coding Assistants AWS Puts Distributed KV Caching Behind an Agent Skill: Up to 40% Cheaper Inference and 80% Faster First Token AI Agents Tencent and King's College London Build an Agent Memory Test From 80,299 Real Group-Chat Messages News Tesla Starts FSD v15 With a Generative Reality View and a 25x Intervention Claim It Has Not Published

Microsoft Turns Three USB4-Cabled PCs Into One AI Machine: Qwen3-235B Runs at Up to 22 Tokens a Second Across 384GB of Ordinary Memory

Microsoft Turns Three USB4-Cabled PCs Into One AI Machine: Qwen3-235B Runs at Up to 22 Tokens a Second Across 384GB of Ordinary Memory

Microsoft has enabled RDMA over USB4 in Windows 11, letting three 128GB PCs pool memory over standard cables to run Qwen3-235B-A22B at 18.5 tokens per second in lab tests, up to 21.98 in AMD-reported runs. Round-trip latency of 28-50 microseconds is about a quarter of the UDP Ethernet figure. All figures are vendor-reported.

Microsoft has switched on RDMA over USB4 in Windows 11, a feature that lets several ordinary PCs connected with standard USB4 cables pool their memory and run a single AI model that would not fit in any one of them, with no dedicated network adapters, no switches and no third-party drivers.

The company's published tests show what that means in practice. Three AMD Ryzen AI Max+ 395 systems, each with 128GB of unified memory, ran the open-weight Qwen3-235B-A22B model in 4-bit quantization at 18.5 tokens per second in Microsoft's lab measurements, with AMD reporting 21.98 tokens per second in its own testing. A 235-billion-parameter model does not fit in 128GB; across three machines it does.

Intel's reference configuration points the same direction at smaller scale. Three Intel Core Ultra Series 3 systems with 64GB of memory each ran GPT-OSS-120B at 49.4 tokens per second, and a four-machine setup reached 54.2. Again, the point is not raw speed but feasibility: a 120-billion-parameter model on machines whose individual memory tops out at 64GB.

The enabling numbers are the latency ones. Microsoft measured round-trip RDMA latency of 28 to 50 microseconds between two machines over USB4, against 116 to 194 microseconds for conventional UDP-based Ethernet on the same physical link, roughly a quarter of the delay. Tensor-parallel inference swaps activations between machines many times per token, which is why the company argues that a low-latency direct memory path riding a link rated up to 80Gbps is what makes multi-PC inference usable at all.

Deployment is currently for enthusiasts rather than consumers. The feature sits in the Windows Insider Experimental channel, requires registry edits and, per Chinese-language write-ups of the preview, disabling Secure Boot. Microsoft recommends a fully-meshed topology, a direct cable between every pair of machines, over daisy-chaining, which visibly hurts performance. Inference frameworks that support the NetworkDirect interface work without code changes, and Microsoft has open-sourced a llama.cpp-based test harness.

All performance figures are vendor-reported and have not been independently verified. But the direction is notable: the memory wall that has pushed local AI toward expensive unified-memory machines and cloud rental is now being attacked with USB cables and spare laptops. It will not outrank a real GPU cluster, yet for hobbyists and small teams it moves running the big open model at home from a hardware purchasing decision to a cabling one.

Comments (0)

Log in to join the discussion

Log In

No comments yet