跳到主要内容Skip to main content

← 返回硬件算力← Back to Compute

整机Systems

NVIDIA DGX SparkNVIDIA DGX Spark

回答桌面级统一内存机器的内存、功耗与体积:128GB 统一内存是它和消费级显卡的根本差别,模型不必先切进显存。官方给出的「最多 200B 参数」是推理口径、且为厂商声明,不是实测;多机互联最多 4 台。不回答训练可行性:微调上限官方写作 70B 参数级。Answers the memory, power and footprint of a desktop unified-memory machine: 128 GB of coherent memory is what separates it from consumer graphics cards, since the model need not be staged into dedicated VRAM first. The stated "up to 200B parameters" is an inference figure and a vendor claim rather than a measurement, and at most four units can be linked. It does not answer training feasibility: the vendor puts fine-tuning at up to 70B parameters.

关键参数Key specs

architecture
NVIDIA Grace Blackwell (GB10)
CPU
20-core Arm: 10 Cortex-X925 + 10 Cortex-A725
memory
128 GB LPDDR5x, coherent unified
memory bandwidth
273 GB/s
tensor performance
up to 1 PFLOP FP4 (with sparsity)
power supply
240 W; GB10 TDP 140 W
dimensions
150 x 150 x 50.5 mm; 1.2 kg
storage
up to 4 TB NVMe M.2
networking
ConnectX-7 at 200 Gbps; 10 GbE; WiFi 7

官方原文怎么说What the source says

Tensor Performance1 Up to 1 PFLOP FP4
1 https://www.nvidia.com/en-us/products/workstations/dgx-spark/
System Memory 64 GB LPDDR5X* or 128 GB LPDDR5x, coherent unified system memory
2 https://www.nvidia.com/en-us/products/workstations/dgx-spark/
Power Supply 240 Watts
3 https://www.nvidia.com/en-us/products/workstations/dgx-spark/

资料与许可Source and licence

资料时间Source checked
2026-11-07
许可 / 类型Licence / kind
official-spec-page
许可说明Licence evidence
https://www.nvidia.com/en-us/products/workstations/dgx-spark/
类目Category
整机Systems

去官网看原页Open the official page →

← 返回硬件算力← Back to Compute