Microsoft has priced and dated the Surface Laptop Ultra - its first device built on Nvidia’s RTX Spark Arm chip - and the laptop starts at $2,599. Preorders opened on October 7 and units ship October 16, so anyone deciding whether to wait for this machine instead of buying a Mac Mini or a used RTX 4090 has about eight days to make up their mind (The Verge; Ars Technica).
The Hardware
The Surface Laptop Ultra is built around Nvidia’s RTX Spark, a Blackwell-architecture system-on-chip that Nvidia says powers “the world’s first Windows PCs purpose-built for personal agents” (NVIDIA Newsroom). The top-end RTX Spark pairs a Blackwell RTX GPU with 6,144 CUDA cores and fifth-generation Tensor Cores with FP4 precision, a 20-core Grace CPU, and up to 128GB of unified LPDDR5x memory, fused by NVLink (NVIDIA Newsroom; NVIDIA Blog).
Surface Laptop Ultra buyers do not get the full 128GB SKU on the cheap. The $2,599 entry model comes with 24GB of RAM and 512GB of storage (The Verge); The Verge’s coverage lists its CPU as 8-core in one item and 18-core in another. TechCrunch reports two base models, starting at about $2,600 and $3,700, with configurations up to $5,900, and says Microsoft reported the highest-end device already out of stock (TechCrunch). Ars reports that higher configurations include either a 5,120-core or 6,144-core Blackwell GPU and top out at 128GB of unified memory - the variable that decides what fits on-device (Ars Technica).
Microsoft also revealed a second machine: the Surface RTX Spark Dev Box, a $5,999 mini-PC “designed to meet the needs of frontier developers.” It carries the 128GB unified-memory configuration and “claims one petaflop (that’s 1,000 teraflops) of AI compute performance,” per Ars Technica (Ars Technica). The Verge lists the same $5,999 starting price and says the Dev Box is available for preorder ahead of a November ship date (The Verge). TechCrunch rounds the figure slightly differently: it “starts priced at $6,000” (TechCrunch).
What It Actually Runs
For local AI, the question is whether the usual software stack - llama.cpp, Ollama, LM Studio, vLLM and open model families - runs well on the new silicon. Microsoft is shipping Surface RTX Spark machines with “native support for local frameworks like llama.cpp and models from the Deepseek and Nvidia Nemotron families,” per Ars (Ars Technica). That is the most practical answer for readers wondering whether capable models can run offline on these machines: Microsoft says yes, with the right model size and the right RTX Spark configuration, though independent tests have not yet landed.
Because the GPU and CPU share the same LPDDR5x pool, the strict VRAM limits of a discrete Nvidia card do not apply. A 70B model quantized to about 4.5 bits per weight needs roughly 39 GB (about 37 GiB) for its weights, so the 128GB configurations (RAM sizes are binary, so 128 GiB) hold it entirely in memory with headroom for context; 7B and 13B models fit easily. Ars notes that the unified memory design is what let Microsoft show Gears of War: E-Day running on the Surface Laptop Ultra - “even without a traditional gaming GPU, AAA titles are on the table” (Ars Technica). On the $2,599 base config the arithmetic is tighter: a 30B-class model at about 4.5 bits per weight needs roughly 17 GB (about 16 GiB) for weights alone, out of 24GB (24 GiB) that the operating system and CPU also share, leaving little room for context.
The pitch is broader than inference. Microsoft is repositioning Windows 11 around what it calls “Hybrid Intelligence,” a term that includes a rebuilt Copilot split into Home, Code, and Autopilot tabs. Autopilot is the agent-oversight surface; Code is meant to let non-developers prompt their way to widgets and Windows apps; Home is the conversational front door (Ars Technica). Satya Nadella made the framing explicit at the San Francisco event. Per TechCrunch’s Julie Bort, he told the audience: “One of the things we realized in the last 3-4 years is that just having a model doesn’t do much for anything. You really do need to orchestrate, and you need to have memory outside of the model. You need to have this harnessed layer that is able to take multiple models plus context, plus memory, and the action space” (TechCrunch).
The Trade-Offs
Two things to weigh before pre-ordering. First, the price ladder versus alternatives. A $2,599 Surface Laptop Ultra with 24GB is not a workstation, and for sustained 70B inference a 128GB configuration such as the $5,999 Dev Box is the realistic target. At those prices a desktop GPU build or a high-memory Mac is a natural comparison, and no independent throughput numbers exist yet to settle it. The Surface value is portability plus Microsoft’s promise of native llama.cpp support and DeepSeek and Nemotron models out of the box.
Second, the OS cost. Microsoft paired the hardware reveal with Microsoft Execution Containers (MXC), a security framework designed to keep agent activities confined to a sandbox, with per-agent guardrails on what each agent can access. Ars reports it can route a workload to a process container, a session container, a WSL container, or an experimental hardware-backed MicroVM (Ars Technica). That is a potential privacy improvement for an agent beat where recent weeks have produced backdoored edited-model demonstrations, though how much it helps depends on how agents and admins use it. TechCrunch reports Nadella said Execution Containers will be available for all Windows 11 users, not just Surface buyers (TechCrunch).
What This Means
For local-AI readers, RTX Spark is Nvidia’s Windows answer to large unified-memory machines such as Apple’s Mac Studio and AMD’s Strix Halo systems. RTX Spark is a Blackwell-class accelerator with the full Nvidia software stack - CUDA, RTX, TensorRT, FP4, NVLink-C2C - inside a Windows laptop you can carry to a coffee shop. Jensen Huang’s framing in the Nvidia Newsroom release is that RTX Spark brings “everything NVIDIA has built - CUDA, RTX, our AI platform - into a single superchip” (NVIDIA Newsroom). llama.cpp founder Georgi Gerganov is quoted in the same release, and Adobe, ComfyUI, Blackmagic Design, OTOY and others are named as embracing the platform; if their pre-launch commitments hold, llama.cpp, Ollama, and Hugging Face’s transformers ecosystem should follow the same drop-in path the DGX Spark already proved out.
For privacy readers, the bigger story is Execution Containers. The site has tracked a steady drumbeat of agent jailbreaks and supply-chain compromises over the last year; an OS-level containment primitive available to all Windows 11 users is more consequential than any one laptop, because it changes the threat model for the millions of existing users who will never buy a $2,599 Surface.
For hardware buyers: do not pre-order the $2,599 model and expect it to replace a desktop. Wait for independent benchmarks of the base and top configurations once the 16th passes, especially for quantized 70B inference, where memory bandwidth and CPU offload matter as much as CUDA cores.
The Bottom Line
The Surface Laptop Ultra brings Nvidia’s RTX Spark and up to 128GB of unified memory to a Windows laptop, enough headroom on paper for large open-weight models, and the Dev Box is the 128GB option for developers. Hold off on the base model until RTX Spark memory-bandwidth numbers and real 70B-inference benchmarks land.
Related on Intelligibberish
- Local AI - more coverage of self-hosted models, hardware picks, and licensing.