The honest headline first: these are different tools that the market insists on cross-shopping. One box is a measured, boring workhorse for the model class most people actually run. The pair of the other is the only desk-format way we know to serve the largest open MoE class — with real operational sharp edges. We own and measured both; nobody in this comparison’s search results does.
Why is this comparison so hard to find measured?
Because it is genuinely awkward to do honestly. The two platforms want different runtimes, favor different model classes, and every published head-to-head we found either reruns vendor numbers or quotes two incompatible community figures side by side — which is how benchmark folklore is born. What follows keeps the two boxes in separate, clearly-scoped columns, and the last section names the measurement that would join them properly.
What the Strix Halo box actually did
One Ryzen AI Max+ 395 unit with 128 GB unified memory, llama.cpp pinned by digest, serving a 35B-class MoE. Everyday requests: first answer token in 210msunit_replicated. Four simultaneous chats: 338msrepeated to the first word, completion holding at 100.0% of requestsrepeated even at eight streams. A 32k-token document costs 33965msrepeated up front, and three continuous hours of serving held pace at 30.0ms/tokensingle_run. The full tables are in the benchmark repository and the 128 GB report.
What the DGX Spark pair actually did
Two GB10 units over a 200G link served DeepSeek-V4-Flash — a 284B-parameter MoE — through vLLM, stably enough to publish the raw runs and the recipe with its traps marked. The pair walked a context curve to a million tokens and told the truth about the bill: decode plateaus at depth, but the first fill of a million-token window is an event you schedule, not a request you fire. Bring-up was real work — a kernel-selection flag the automatic mode skips separates the fast configuration from the one most people measure, and the stock GPU monitoring half-works at best. The buyer’s answer, including who should not buy one, is its own page.
Which box for which workload?
From what we measured, not from spec sheets. A personal assistant, a small team’s chat box, document Q&A in the tens-of-thousands-of-tokens range, JSON automation: the Strix Halo box does all of it today, quietly, with the numbers above. Serving the largest open MoE class under your own roof, or long-context research where a million-token window amortizes: that is what the Spark pair demonstrably did, and nothing in our fleet at this size matched it. If your question is “which one for a home assistant”, you are choosing between a measured yes and an overqualified maybe. If your question is “can I serve the frontier open models locally”, only one of these platforms did it in our lab — as a pair, with seams.
Why don’t our numbers match the reviews you read?
Because most published figures for both platforms are configs in disguise: unstated workload profiles, moved defaults, pre-update firmware. We wrote a reconciliation of the disagreeing Spark numbers instead of adding another orphan figure, and a protocol for publishing numbers that can be disagreed with. Both apply to any figure on this page.
What we have NOT measured
The clean comparison — same model, same runtime, same workload, both boxes, one harness — does not exist yet, here or anywhere we could find. Our Strix lane ran Qwen3.6 and gemma-4 under llama.cpp; our Spark lane ran DeepSeek-V4-Flash under vLLM. Any table putting those numbers in adjacent columns would be manufacturing the exact folklore we exist to debunk, so this page does not contain one. The same-harness cross-device cell is planned; when it lands, its claims will carry system-level comparison scope and this page will be superseded by something better. Until then: two honest columns beat one fake table.
Every Strix figure above has a permanent page with raw runs in the claim registry; every Spark statement links its published run repository.