Acer Veriton GN100 Cluster Cable: 0.5m QSFP112 400G DAC
To cluster two Acer Veriton GN100 AI mini workstations you need one 0.5m QSFP112 400G passive DAC cable in the QSFP112 port on each unit. The Veriton GN100 packs NVIDIA's GB10 Grace Blackwell superchip into a compact, value-priced desktop, and it carries the same ConnectX-7 NIC as the DGX Spark, so it takes the exact cable NVIDIA approves in its Spark Stacking documentation (Amphenol NJAAKK0006 / Luxshare LMTQF022-SD-R spec). Petronella Technology Group, Inc. keeps it in stock at $159 with free US shipping, while distributors quote $179 to $229 and are usually backordered.
The Veriton GN100 is Acer's value entry into the GB10 lineup, pairing the 20-core Arm and Blackwell GB20B GPU superchip with 128 GB of unified LPDDR5x memory and up to 4 TB of PCIe Gen5 NVMe storage in a mini-PC footprint. Its low cost of entry makes it a natural pick for a first pair of nodes, and the moment you add a second GN100 the only missing piece is this cable. Acer exposes NVIDIA's GB10 clustering over two QSFP112 ports on the onboard ConnectX-7 NIC, the same interconnect as every other GB10 machine.
| Cable | 0.5m QSFP112 400G passive direct-attach copper (DAC) |
| Approved spec | Amphenol NJAAKK0006 / Luxshare LMTQF022-SD-R (NVIDIA Spark Stacking docs) |
| Fits | Both QSFP112 ports on the Acer Veriton GN100 ConnectX-7 NIC |
| Platform | NVIDIA GB10 Grace Blackwell, 128 GB LPDDR5x, up to 4 TB Gen5 NVMe |
| For two GN100 units | One cable |
| For a three-node ring | Three cables (switchless, each box uses both ports) |
| Price | $159, free US shipping (in stock) |
Clustering Acer Veriton GN100 units: how many cables and when you need a switch
Each Veriton GN100 has two QSFP112 ports, so it follows the NVIDIA-documented GB10 topology: two units link directly with one cable, and three units form a switchless ring with three cables, each box using both ports for full pairwise connectivity. Three nodes is the switchless ceiling; with only two ports per unit, four or more GN100 units need a 200G-class QSFP switch. Clustering pools memory so a model too large for one 128 GB node runs across two or three boxes. It is a capacity play, not a raw speed boost, since each link runs around 25 GB/s, which is exactly what memory-bound inference and fine-tuning on larger models needs. Because every GB10 system shares the ConnectX-7 NIC and QSFP112 spec, a GN100 also clusters with a DGX Spark or any other OEM box over the same cable.