NVIDIA RTX Spark N1X 笔记本实测：128 GB 统一内存跑 Qwen3.8 27B 本地智能体
NVIDIA 把 DGX Spark 的 GB10 芯片塞进了 Windows 笔记本，128 GB 内存能本地跑 77 GB 的 Ling 3.0 Flash，实测比 M5 Pro 快一倍，搞本地部署的看看。
Artificial Analysis 测试了搭载 NVIDIA RTX Spark N1X 芯片的笔记本原型（15 英寸 Surface Laptop Ultra，128 GB，5,900 美元），芯片基于 DGX Spark 的 GB10，含 20 核 Arm CPU 和 6,144 核 Blackwell GPU。在 AA-AgentPerf-Local 本地智能体测试中，它跑 Qwen3.8 27B 用时 18.7 分钟，接近 DGX Spark 的 17.3 分钟，比 M5 Pro MacBook Pro 的 37.6 分钟快 2.0 倍。跑 Qwen3.6 35B A3B 用时 7.6 分钟，比 MacBook Pro 的 11.9 分钟快 1.6 倍。77 GB 权重的 Ling 3.0 Flash 也只适合这台机器，用 15.3 分钟完成，而 MacBook Pro 和 RTX 5090 装不下该模型。RTX 5090 桌面端仍是最快的，Qwen3.8 27B 上仅用 4.9 分钟。
NVIDIA's RTX Spark N1X puts up to 128 GB of unified memory and a Blackwell GPU in a Windows laptop. In our first AA-AgentPerf-Local results, an RTX Spark laptop completes our local agent workload on Qwen3.8 27B in 18.7 minutes
RTX Spark's N1X chip is essentially the GB10 from DGX Spark (20-core Arm CPU, 6,144-core Blackwell GPU), with up to 128 GB of memory at 300 GB/s. We tested a prototype 15-inch Surface Laptop Ultra (128 GB, $5,900), plugged in with Windows set to high-performance mode, using NVIDIA's published llama.cpp recipes where available
Key results:
➤ On Qwen3.8 27B the RTX Spark laptop finishes our default workload (8 recorded agent tasks, 168 model turns) in 18.7 minutes, close to DGX Spark (17.3), 2.0x faster than the MacBook Pro (M5 Pro, 64 GB, 37.6) and 1.8x faster than the AMD Ryzen AI Halo (34.5). The GeForce RTX 5090 desktop is fastest, at 4.9 minutes
➤ On Qwen3.6 35B A3B it takes 7.6 minutes, close to DGX Spark (7.3), and 1.6x faster than the MacBook Pro (11.9)
➤ On Ling 3.0 Flash, the largest current model we test, it takes 15.3 minutes, close to DGX Spark (14.9) and 1.6x faster than the Ryzen AI Halo (25.1). Its 77 GB of weights do not fit on the MacBook Pro or the RTX 5090
Read the full analysis: https://t.co/72xrYNrtw8
