ASUS Ascent GX10 128 GB specifications
Specification | Detail |
|---|---|
Platform | NVIDIA GB10 Grace Blackwell |
CPU | 20 Arm cores: 10 Cortex-X925 + 10 Cortex-A725 |
GPU | Integrated NVIDIA Blackwell, 5th-generation Tensor cores |
Unified CPU–GPU memory | 128 GB LPDDR5X-8533 |
Stated memory bandwidth | 273 GB/s |
Theoretical AI compute | Up to 1 petaFLOP in FP4 with sparsity; not measured application throughput |
SSD slot | 1 × M.2; up to 4 TB depending on configuration |
Wired networking | 1 × 10 Gb/s Ethernet; NVIDIA ConnectX-7 SmartNIC for interconnection |
Wireless | Wi-Fi 7 2×2; Bluetooth 5.4 |
USB | 4 × USB-C 20 Gb/s: 3 with DisplayPort Alt Mode and 1 with PD 3.1 EPR power input |
Video | HDMI 2.1a; DisplayPort 2.1 through compatible USB-C ports |
System | NVIDIA DGX OS, environnement Linux pour Arm |
Power adapter | 240 W; rated power, not measured consumption |
Dimensions and weight | 150 × 150 × 51 mm; 1.48 kg |
Finish | Stellar Grey |
Memory at the heart of the proposition
The GX10 combines a twenty-core Arm processor with an integrated NVIDIA Blackwell GPU. Its main appeal is its memory capacity: the 128 GB are shared between CPU and GPU. They should not be read as 128 GB of graphics memory plus a separate quantity of system RAM.
This architecture opens possibilities for loading large models, but capacity alone does not determine responsiveness. Weight precision, context length and concurrent requests all affect requirements. The useful question when choosing a machine is still which model will actually be used and what response time is acceptable.
A small enclosure with specialised connectivity
ASUS fits this platform into a 150 × 150 × 51 mm enclosure. The GX10 includes 10 Gb/s Ethernet, Wi-Fi 7 and an NVIDIA ConnectX-7 interface. The latter is useful in development configurations requiring appropriate interconnection; it does not by itself turn multiple machines into a single computer.
The catalogue consulted lists three 128 GB configurations: GX10-GG0003BN with 1 TB of storage, GX10-GG0026BN with 2 TB and GX10-GG0027BN with 4 TB. For keeping multiple models, different quantisations and datasets, storage capacity deserves as much attention as the processor specifications.
Choose the platform alongside its software
The announced operating system is NVIDIA DGX OS. Before buying, check that the required libraries, containers and dependencies are available for this Arm architecture. An application available on a Windows x86 PC does not become compatible merely because an NVIDIA GPU is present.
What 128 GB actually enables
Memory capacity is useful when model weights, context cache and other tasks must remain available together. It does not by itself specify how many requests can be served simultaneously. A document assistant also needs room for the search engine, indexes and document-preparation services.
The GX10 can act as a remotely accessible development machine: the usual workstation retains the code editor and interface, while calculations run on Linux. This separates client-machine compatibility from the software running on the station. Deployment should plan for updates, backups and access rights.
SKUs and manufacturer part numbers
Model | Manufacturer part number | SSD |
|---|---|---|
GX10-GG0003BN | 90MS0371-M00030 | 1 TB NVMe SSD, PCIe 4.0 |
GX10-GG0026BN | 90MS0371-M000U0 | 2 TB NVMe SSD, PCIe 4.0 |
GX10-GG0027BN | 90MS0371-M000V0 | 4 TB NVMe SSD, PCIe 5.0 |
Explore further
ASUS Ascent GX10 64 GB: who is this new configuration for?
ASUS ExpertCenter Pro ET900N G3: a GB300 workstation for large-scale AI projects
GX10 or ET900N G3: how to choose your ASUS machine for local AI
Key takeaways
The GX10 128 GB therefore targets developers and teams with a specific local AI use case. Its format makes installation easier; its capabilities make sense with a suitable software stack.