Zotac ZBOX CI662 nano Fanless mini-PC Review: Second Stab at Silencing Succeeds

Storage and Networking Performance

Networking and storage are two major aspects which influence our experience with any computing system. This section presents results from our evaluation of these aspects in the Zotac ZBOX CI662 nano. On the storage side, one option would be repetition of our strenuous SSD review tests on the drive(s) in the PC. Fortunately, to avoid that overkill, UL PCMark 10 has a Full System Drive Benchmark storage test certain common workloads such as booting, loading games, and document processing are replayed on the target drive. The average access times and bandwidth numbers are recorded for each trace and the overall numbers contribute to a benchmark score. For older systems, we have scores from the PCMark 8 storage bench (which we continue to process on newer machines as we build up the database of PCMark 10 storage bench results).

In case of single drive systems, we attempt to allocate 180GB to the primary partition, and leave the remaining space on the drive as a secondary partition. For dual-drive systems, the OS drive is the primary drive, while the other is categorized as the secondary one. Since PCMark 10 requires 80GB of free space at the minimum for processing the Full System Drive Benchmark, we are able to process the benchmark on both the primary and secondary drive in only some of the evaluated systems. The results are presented below.

The PCMark 8 storage bench doesn't indicate much difference between the different drives (SATA or NVMe) in the subsystem score, but the bandwidth numbers clearly differentiate between the SATA and NVMe-class drives. The CI6xx nano series doesn't support NVMe drives - only 2.5" drives are supported, and we have one of the best in that class used in the CI662 nano review sample.

The SK hynix Gold S31 is the only SATA SSD to be subject to the PCMark 10 Storage Bench as part of our systems evaluation process. We know it is not meant to produce the same level of performance as the NVMe drives used in the Frost Canyon NUC or the DIY Bean Canyon NUC / Akasa Turing kit, but it still returns respectable access times that are essential for a responsive system.

On the networking side, we restricted ourselves to the evaluation of the WLAN component. Our standard test router is the Netgear Nighthawk AX12 RAX120 configured with both 2.4 GHz and 5 GHz networks. The router is placed approximately 11 ft. away with a direct line-of-sight to the PC under test. A wired client (Zotac MI553, with an Akitio T3-10G NBASE-T Thunderbolt 3 adapter) is connected to the 5GbE port of the RAX120 and serves as one endpoint for iperf evaluation.

The RAX120 can be explicitly configured to connect over a DFS channel. This works in the absence of any radar presence in the vicinity. We configured the router to operate in Channel 64 (DFS) after ensuring that no nearby wireless networks were operating in that channel (in order to avoid benchmarking interference as much as possible). In such a scenario, the Zotac ZBOX CI662 nano connected with the following parameters.

A script to run iPerf3 with 1, 2, 4, 8, and 16 parallel streams between the Zotac ZBOX CI662 nano and the Zotac ZBOX MI553 was processed - the first set for TX alone, followed by another set for RX, and finally a third set with bidirectional traffic.

Due to the 433 Mbps single-stream 802.11ac configuration, we can expect around 370 Mbps of best-case throughput via the Wireless-AC 9462 in the Zotac ZBOX CI662 nano. The table below presents the iPerf3 benchmark results obtained in the above testing scenario.

The numbers presented above are slightly lesser than the average segment bandwidths noted, as the data in the graph is computed from the network interface's counters, while iPerf reports results based only on the traffic sent by it alone.