Supercomputers/Systems/Sharon AI Melbourne B200 Cluster
Australia · under construction · mixed
Sharon AI Melbourne B200 Cluster
Also known as Sharon AI NEXTDC M3 1, 000-GPU B200 cluster
Operated by Sharon AI at NEXTDC M3 Data Centre (Melbourne) .
Researched with AI assistance, checked by scripts. These rows were researched by AI agents reading public operator, laboratory and vendor sources, appended by scripts and checked by automated validation; no subject-matter expert has reviewed them (how this site is made). A mechanical second-reader pass has since fetched every cited source: 1350 of 1581 systems have a readable citation that names them, and 64 are genuinely weakly sourced. Every claim carries its source and a confidence tier. Treat anything below verified as a lead, not a citation.
Measured performance
- Rmax
- -
- Rpeak
- -
- Rmax ÷ Rpeak
- -
- Cores
- -
- Power
- -
- Per watt
- - GF/W
Figures are as last publicly reported for the configuration described below, not a live measurement. Where a system was upgraded in place, the post-upgrade configuration is shown and the earlier one appears in the timeline.
What this machine is made of
One row per supplier relationship. “Supplier at build” is the company that shipped the part at the time; where that company has since been acquired, the parent it rolls up to today is shown beside it. That distinction is what makes ticker-level aggregation possible across a thirty-year dataset.
| Role | Part | Supplier at build | Quantity | Confidence | Source |
|---|---|---|---|---|---|
| Integrator | - Lenovo TruScale Infrastructure-as-a-Service, high-density server engineering | Lenovo | - | Reported | itwire.comintelligentcio.com |
| Accelerator | NVIDIA B200 SXM Accelerators CUDA (Blackwell) · TSMC 4NP · 1,000 W 1,000-GPU NVIDIA B200 cluster, eight Blackwell GPUs per node | NVIDIA | 1,000 reported | Reported | itwire.comintelligentcio.com |
| Storage | VAST Data Platform Storage Disaggregated shared-everything VAST Data high-performance storage fabric | VAST Data | - | Reported | itwire.com |
AI datacenter metrics
Figures beyond an accelerator count, each with who stated it. What can and cannot be compared across AI datacenters.
| Metric | Value | As of | Basis | Note | Source |
|---|---|---|---|---|---|
| Accelerators | 1,000 accelerators | 2026-03-10 | Operator stated | Lenovo and Sharon AI describe a 1,000-GPU NVIDIA B200 cluster; deployment described as expected. | itwire.comintelligentcio.com |
The read
A 1,000-GPU NVIDIA B200 cluster for Sharon AI at NEXTDC's Tier IV M3 data centre in Melbourne, delivered by Lenovo as its largest TruScale Infrastructure-as-a-Service engagement and built with VAST Data storage. Lenovo's wording on 10 March 2026 is 'expected deployment' (iTWire, Intelligent CIO), while Technology Decisions leads with Sharon AI having 'commissioned' the cluster and then calls the deployment expected, so the go-live date is unconfirmed and the status stays under_construction. The material says each node carries eight Blackwell GPUs on fifth-generation NVLink, which would imply about 125 nodes if all 1,000 GPUs are in 8-GPU nodes (derived, not stated). Sharon AI's existing local fleet is A40, L40S, H100 and H200, and Lenovo says B300 and GB300 platforms follow in 2026. No MW figure is given for this cluster. Reported tier: one Lenovo announcement carried by three outlets.
Timeline
- 2026-03-10 Announced source
Site & facility
Change history
- 2026-10-29 Added Sharon AI Melbourne B200 Cluster
Nearby in scale
The machines closest to Sharon AI Melbourne B200 Cluster by accelerator count, smaller to larger.
- Siam.AI Cloud H100 Cluster · Thailand, operational · 1,000 accelerators
- Koukaryoku PHY H200 Container DC · Japan, operational · 1,000 accelerators
- Moore Threads KUAE 1,000-GPU Cluster · China, operational · 1,000 accelerators
- Lintasarta GPU Merdeka · Indonesia, operational · 1,000 accelerators
- MeluXina-AI · Luxembourg, planned · 1,008 accelerators
- LillyPod · USA, operational · 1,016 accelerators
Related systems
Same accelerator
- E2E Chennai B200 Cluster · India, operational
- Firebird Armenian AI Factory (DC-1) · Armenia, operational, 2026
- Industrial AI Cloud · Germany, operational, 2026
- Jairu · Brazil, operational, 2026
- Naver B200 4K Cluster · South Korea, operational, 2026
- Nexus (Georgia Tech) · USA, operational, 2026
Further reading
Inside a node
Why accelerators exist, what the memory hierarchy costs, and how the CPU and accelerator merged onto one package.
Operating a supercomputer
Acceptance testing, why "installed" and "in production" are six months apart, and the machine lifecycle.
Storage and I/O
Parallel file systems, why checkpointing dominates the write load, and the metadata failure mode nobody expects.