Systems

Built, tested and handed over working

Every system arrives with its software stack installed and a burn-in report showing 72 hours at full load without fault. Clusters are commissioned and tested on your site, not delivered as a stack of boxes. Any of these can be opened in the configurator and altered.

SUPERCOMPUTERSSystemNo photograph on file

ai rigRefurbished24h burn-in12mo warranty

TF-R4 Open Frame Rig

Processors: AMD Ryzen Threadripper PRO 5975WX
Accelerators: 4 x NVIDIA GeForce RTX 4090 24GB
Cores: 32 total
Memory: 256GB DDR4
Storage: 2x 4TB M.2 NVMe
Fabric: 1x 10GbE
Rack space: 0U
Peak power: 2.4kW · 10A at 230V
Heat rejected: 8,189 BTU/hr

96GB VRAM on an open frame with real spacing between cards
2400W, needs two circuits or a dedicated 20A feed
No ECC and no NVLink; the economics make up for it

Ships with Ubuntu 24.04 LTS · CUDA 12 · vLLM · Ollama

Quoted per order

30 working days

Request a quote Full spec

SUPERCOMPUTERSSystemNo photograph on file

ai workstationRefurbished24h burn-in12mo warranty

TF-W2P Pro Workstation

Processors: AMD Threadripper PRO 7965WX
Accelerators: 2 x NVIDIA RTX A6000 48GB
Cores: 24 total
Memory: 256GB DDR5
Storage: 2x 2TB M.2 NVMe + 1x 7.68TB U.2
Fabric: 2x 10GbE onboard
Rack space: 0U
Peak power: 1.3kW · 5A at 230V
Heat rejected: 4,265 BTU/hr

96GB of ECC VRAM across an NVLink pair
Runs on a single 230V wall socket
The workstation most Pakistani research groups actually need

Ships with Ubuntu 24.04 LTS · CUDA 12 · PyTorch 2 · Docker · JupyterLab

Quoted per order

30 working days

Request a quote Full spec

SUPERCOMPUTERSSystemNo photograph on file

ai rigNew build24h burn-in36mo warranty

TF-R4 Open Frame Rig

Processors: AMD Ryzen Threadripper PRO 5975WX
Accelerators: 4 x NVIDIA GeForce RTX 4090 24GB
Cores: 32 total
Memory: 256GB DDR4
Storage: 2x 4TB M.2 NVMe
Fabric: 1x 10GbE
Rack space: 0U
Peak power: 2.4kW · 10A at 230V
Heat rejected: 8,189 BTU/hr

96GB VRAM on an open frame with real spacing between cards
2400W, needs two circuits or a dedicated 20A feed
No ECC and no NVLink; the economics make up for it

Ships with Ubuntu 24.04 LTS · CUDA 12 · vLLM · Ollama

Quoted per order

30 working days

Request a quote Full spec

SUPERCOMPUTERSSystemNo photograph on file

hpc nodeRefurbished48h burn-in12mo warranty

TF-N2 Compute Node

Processors: 2x AMD EPYC 9354
Accelerators: CPU only
Cores: 64 total
Memory: 768GB DDR5
Storage: 2x 1.92TB U.2 NVMe
Fabric: 1x ConnectX-6 HDR200
Rack space: 1U
Peak power: 0.9kW · 4A at 230V
Heat rejected: 3,071 BTU/hr

64 cores and 768GB in 1U
Stateless boot, add nodes without touching a disk
The unit of growth for a Slurm cluster

Ships with Rocky Linux 9 · Slurm client · OpenMPI · Warewulf stateless boot

Quoted per order

30 working days

Request a quote Full spec

SUPERCOMPUTERSSystemNo photograph on file

ai rigNew build24h burn-in36mo warranty

TF-W2 Creator Rig

Processors: AMD Ryzen 9 9950X
Accelerators: 2 x NVIDIA GeForce RTX 5090 32GB
Cores: 16 total
Memory: 192GB DDR5
Storage: 2x 4TB M.2 NVMe
Fabric: 1x 2.5GbE onboard
Rack space: 0U
Peak power: 1.7kW · 7A at 230V
Heat rejected: 5,800 BTU/hr

64GB of GDDR7 for local model work and rendering
1700W peak, needs a dedicated 15A circuit, not a shared board
Consumer cards: no ECC, no NVLink, but the price reflects that

Ships with Ubuntu 24.04 LTS · CUDA 12 · ComfyUI · Ollama · PyTorch 2

Quoted per order

30 working days

Request a quote Full spec

SUPERCOMPUTERSSystemNo photograph on file

ai workstationNew build24h burn-in36mo warranty

TF-W2P Pro Workstation

Processors: AMD Threadripper PRO 7965WX
Accelerators: 2 x NVIDIA RTX A6000 48GB
Cores: 24 total
Memory: 256GB DDR5
Storage: 2x 2TB M.2 NVMe + 1x 7.68TB U.2
Fabric: 2x 10GbE onboard
Rack space: 0U
Peak power: 1.3kW · 5A at 230V
Heat rejected: 4,265 BTU/hr

96GB of ECC VRAM across an NVLink pair
Runs on a single 230V wall socket
The workstation most Pakistani research groups actually need

Ships with Ubuntu 24.04 LTS · CUDA 12 · PyTorch 2 · Docker · JupyterLab

Quoted per order

30 working days

Request a quote Full spec

SUPERCOMPUTERSSystemNo photograph on file

hpc nodeNew build48h burn-in36mo warranty

TF-N2 Compute Node

Processors: 2x AMD EPYC 9354
Accelerators: CPU only
Cores: 64 total
Memory: 768GB DDR5
Storage: 2x 1.92TB U.2 NVMe
Fabric: 1x ConnectX-6 HDR200
Rack space: 1U
Peak power: 0.9kW · 4A at 230V
Heat rejected: 3,071 BTU/hr

64 cores and 768GB in 1U
Stateless boot, add nodes without touching a disk
The unit of growth for a Slurm cluster

Ships with Rocky Linux 9 · Slurm client · OpenMPI · Warewulf stateless boot

Quoted per order

30 working days

Request a quote Full spec

SUPERCOMPUTERSSystemNo photograph on file

gpu serverNew build48h burn-in36mo warranty

TF-L8 Edge Inference

Processors: AMD EPYC 9124
Accelerators: 8 x NVIDIA L4 24GB
Cores: 16 total
Memory: 256GB DDR5
Storage: 4x 1.92TB U.2 NVMe
Fabric: 2x 25GbE
Rack space: 1U
Peak power: 0.9kW · 4A at 230V
Heat rejected: 3,071 BTU/hr

Eight L4s in 1U on 900W total
No auxiliary GPU power cables anywhere in the box
Fits a colocation cabinet with a normal power allocation

Ships with Ubuntu 22.04 LTS · Triton Inference Server · TensorRT · Prometheus

Quoted per order

30 working days

Request a quote Full spec

SUPERCOMPUTERSSystemNo photograph on file

gpu serverRefurbished48h burn-in12mo warranty

TF-V2 VDI Node

Processors: 2x Intel Xeon Gold 6548Y+
Accelerators: 4 x NVIDIA L40 48GB
Cores: 64 total
Memory: 1TB DDR5
Storage: 8x 3.84TB U.2 NVMe
Fabric: 2x 25GbE
Rack space: 2U
Peak power: 2.4kW · 10A at 230V
Heat rejected: 8,189 BTU/hr

Up to 64 virtual workstations on four L40s
vGPU licensing quoted separately, it is per-user and annual
Designed for engineering firms consolidating CAD seats

Ships with VMware ESXi or Proxmox · NVIDIA vGPU host driver · Horizon or Omnissa

Quoted per order

30 working days

Request a quote Full spec

SUPERCOMPUTERSSystemNo photograph on file

gpu serverRefurbished48h burn-in12mo warranty

TF-4A100 Refurb Trainer

Processors: 2x AMD EPYC 7543
Accelerators: 4 x NVIDIA A100 PCIe 80GB
Cores: 64 total
Memory: 512GB DDR4
Storage: 4x 3.84TB U.2 NVMe
Fabric: 1x ConnectX-6 HDR200
Rack space: 4U
Peak power: 2.6kW · 11A at 230V
Heat rejected: 8,871 BTU/hr

320GB HBM2e for well under half the price of a new node
Every GPU load-tested 48 hours before it ships
The best PKR-per-training-hour we sell

Ships with Ubuntu 22.04 LTS · CUDA 12 · PyTorch 2 · Slurm · NCCL tuned

Quoted per order

30 working days

Request a quote Full spec

SUPERCOMPUTERSSystemNo photograph on file

gpu serverNew build48h burn-in36mo warranty

TF-V2 VDI Node

Processors: 2x Intel Xeon Gold 6548Y+
Accelerators: 4 x NVIDIA L40 48GB
Cores: 64 total
Memory: 1TB DDR5
Storage: 8x 3.84TB U.2 NVMe
Fabric: 2x 25GbE
Rack space: 2U
Peak power: 2.4kW · 10A at 230V
Heat rejected: 8,189 BTU/hr

Up to 64 virtual workstations on four L40s
vGPU licensing quoted separately, it is per-user and annual
Designed for engineering firms consolidating CAD seats

Ships with VMware ESXi or Proxmox · NVIDIA vGPU host driver · Horizon or Omnissa

Quoted per order

30 working days

Request a quote Full spec

SUPERCOMPUTERSSystemNo photograph on file

gpu serverRefurbished48h burn-in12mo warranty

TF-4A100 Refurb Trainer

Processors: 2x AMD EPYC 7543
Accelerators: 4 x NVIDIA A100 PCIe 80GB
Cores: 64 total
Memory: 512GB DDR4
Storage: 4x 3.84TB U.2 NVMe
Fabric: 1x ConnectX-6 HDR200
Rack space: 4U
Peak power: 2.6kW · 11A at 230V
Heat rejected: 8,871 BTU/hr

320GB HBM2e for well under half the price of a new node
Every GPU load-tested 48 hours before it ships
The best PKR-per-training-hour we sell

Ships with Ubuntu 22.04 LTS · CUDA 12 · PyTorch 2 · Slurm · NCCL tuned

Quoted per order

30 working days

Request a quote Full spec

SUPERCOMPUTERSSystemNo photograph on file

ai workstationNew build24h burn-in36mo warranty

TF-W4 AI Workstation

Processors: AMD Threadripper PRO 7975WX
Accelerators: 4 x NVIDIA RTX 6000 Ada 48GB
Cores: 32 total
Memory: 512GB DDR5
Storage: 2x 4TB M.2 NVMe + 2x 7.68TB U.2
Fabric: 2x 10GbE onboard
Rack space: 0U
Peak power: 2.1kW · 9A at 230V
Heat rejected: 7,165 BTU/hr

192GB of ECC VRAM under a desk, on a single 230V circuit
Blower cards so all four stay under 84C in a closed case
Runs on ordinary office power, no rack, no three-phase

Ships with Ubuntu 24.04 LTS · CUDA 12 · PyTorch 2 · Docker · JupyterLab

Quoted per order

30 working days

Request a quote Full spec

SUPERCOMPUTERSSystemNo photograph on file

storage nodeRefurbished72h burn-in12mo warranty

TF-S24 NVMe Storage Node

Processors: 2x AMD EPYC 9354
Accelerators: CPU only
Cores: 64 total
Memory: 512GB DDR5
Storage: 24x 15.36TB U.2 NVMe (368TB raw)
Fabric: 2x ConnectX-6 HDR200
Rack space: 2U
Peak power: 1.8kW · 8A at 230V
Heat rejected: 6,142 BTU/hr

368TB raw NVMe in 2U
NFS over RDMA keeps training GPUs fed
ZFS with dual-parity and hot spares configured before dispatch

Ships with Ubuntu 22.04 LTS · ZFS 2.2 · NFS over RDMA · MinIO S3 gateway

Quoted per order

30 working days

Request a quote Full spec

SUPERCOMPUTERSSystemNo photograph on file

clusterRefurbished96h burn-in12mo warranty

TF-C8 Starter Cluster

Processors: 2x AMD EPYC 9354 per node
Accelerators: CPU only
Cores: 512 total
Memory: 4TB DDR5
Storage: 8x 3.84TB U.2 + 100TB shared
Fabric: HDR200 InfiniBand, QM8700 spine
Rack space: 16U across 8 nodes
Peak power: 9.6kW · 42A at 230V
Heat rejected: 32,755 BTU/hr

512 cores across eight nodes in one rack
Open OnDemand gives researchers a browser interface instead of ssh
Sized for a university department, not a national facility

Ships with Rocky Linux 9 · Slurm · OpenMPI · Warewulf · Open OnDemand

Quoted per order

30 working days

Request a quote Full spec

SUPERCOMPUTERSSystemNo photograph on file

storage nodeNew build72h burn-in36mo warranty

TF-S24 NVMe Storage Node

Processors: 2x AMD EPYC 9354
Accelerators: CPU only
Cores: 64 total
Memory: 512GB DDR5
Storage: 24x 15.36TB U.2 NVMe (368TB raw)
Fabric: 2x ConnectX-6 HDR200
Rack space: 2U
Peak power: 1.8kW · 8A at 230V
Heat rejected: 6,142 BTU/hr

368TB raw NVMe in 2U
NFS over RDMA keeps training GPUs fed
ZFS with dual-parity and hot spares configured before dispatch

Ships with Ubuntu 22.04 LTS · ZFS 2.2 · NFS over RDMA · MinIO S3 gateway

Quoted per order

30 working days

Request a quote Full spec

SUPERCOMPUTERSSystemNo photograph on file

gpu serverRefurbished48h burn-in12mo warranty

TF-8L40S Inference Node

Processors: 2x AMD EPYC 9354
Accelerators: 8 x NVIDIA L40S 48GB
Cores: 64 total
Memory: 1TB DDR5
Storage: 10x 3.84TB U.2 NVMe
Fabric: 2x ConnectX-6 HDR200 + 2x 25GbE
Rack space: 4U
Peak power: 4.8kW · 21A at 230V
Heat rejected: 16,378 BTU/hr

384GB of GDDR6 ECC across eight cards
Air-cooled in 4U, no facility water needed
The sensible first production inference box

Ships with Ubuntu 22.04 LTS · CUDA 12 · vLLM · Triton Inference Server · Prometheus + Grafana

Quoted per order

60 working days

Request a quote Full spec

SUPERCOMPUTERSSystemNo photograph on file

clusterNew build96h burn-in36mo warranty

TF-C8 Starter Cluster

Processors: 2x AMD EPYC 9354 per node
Accelerators: CPU only
Cores: 512 total
Memory: 4TB DDR5
Storage: 8x 3.84TB U.2 + 100TB shared
Fabric: HDR200 InfiniBand, QM8700 spine
Rack space: 16U across 8 nodes
Peak power: 9.6kW · 42A at 230V
Heat rejected: 32,755 BTU/hr

512 cores across eight nodes in one rack
Open OnDemand gives researchers a browser interface instead of ssh
Sized for a university department, not a national facility

Ships with Rocky Linux 9 · Slurm · OpenMPI · Warewulf · Open OnDemand

Quoted per order

30 working days

Request a quote Full spec

SUPERCOMPUTERSSystemNo photograph on file

gpu serverNew build48h burn-in36mo warranty

TF-8L40S Inference Node

Processors: 2x AMD EPYC 9354
Accelerators: 8 x NVIDIA L40S 48GB
Cores: 64 total
Memory: 1TB DDR5
Storage: 10x 3.84TB U.2 NVMe
Fabric: 2x ConnectX-6 HDR200 + 2x 25GbE
Rack space: 4U
Peak power: 4.8kW · 21A at 230V
Heat rejected: 16,378 BTU/hr

384GB of GDDR6 ECC across eight cards
Air-cooled in 4U, no facility water needed
The sensible first production inference box

Ships with Ubuntu 22.04 LTS · CUDA 12 · vLLM · Triton Inference Server · Prometheus + Grafana

Quoted per order

60 working days

Request a quote Full spec

SUPERCOMPUTERSSystemNo photograph on file

clusterRefurbished96h burn-in12mo warranty

TF-C16 CPU Cluster

Processors: 2x AMD EPYC 9654 per node
Accelerators: CPU only
Cores: 3072 total
Memory: 12TB DDR5
Storage: 16x 7.68TB U.2 NVMe + 200TB shared
Fabric: HDR200 InfiniBand fat-tree, QM8700 spine
Rack space: 32U across 16 nodes
Peak power: 22.0kW · 96A at 230V
Heat rejected: 75,064 BTU/hr

3072 cores and 12TB of RAM across sixteen nodes
Non-blocking HDR200 fat-tree, cabled and validated on site
Delivered as two racks: compute plus storage and head

Ships with Rocky Linux 9 · Slurm · OpenMPI · Lustre client · Warewulf provisioning

Quoted per order

60 working days

Request a quote Full spec

SUPERCOMPUTERSSystemNo photograph on file

clusterNew build96h burn-in36mo warranty

TF-C16 CPU Cluster

Processors: 2x AMD EPYC 9654 per node
Accelerators: CPU only
Cores: 3072 total
Memory: 12TB DDR5
Storage: 16x 7.68TB U.2 NVMe + 200TB shared
Fabric: HDR200 InfiniBand fat-tree, QM8700 spine
Rack space: 32U across 16 nodes
Peak power: 22.0kW · 96A at 230V
Heat rejected: 75,064 BTU/hr

3072 cores and 12TB of RAM across sixteen nodes
Non-blocking HDR200 fat-tree, cabled and validated on site
Delivered as two racks: compute plus storage and head

Ships with Rocky Linux 9 · Slurm · OpenMPI · Lustre client · Warewulf provisioning

Quoted per order

60 working days

Request a quote Full spec

SUPERCOMPUTERSSystemNo photograph on file

gpu serverRefurbished72h burn-in12mo warranty

TF-8H100 HGX Node

Processors: 2x Intel Xeon Platinum 8480+
Accelerators: 8 x NVIDIA H100 SXM5 80GB
Cores: 112 total
Memory: 2TB DDR5
Storage: 8x 7.68TB U.2 NVMe
Fabric: 8x ConnectX-7 NDR400 + 2x 100GbE
Rack space: 8U
Peak power: 10.2kW · 44A at 230V
Heat rejected: 34,802 BTU/hr

8-way NVLink all-to-all, 900 GB/s per GPU
Delivered racked, cabled and burned in for 72 hours
10.2kW peak, three-phase and real cooling are prerequisites, not options

Ships with Ubuntu 22.04 LTS · NVIDIA driver + CUDA 12 · NVIDIA Container Toolkit · Slurm · NCCL tuned

Quoted per order

60 working days

Request a quote Full spec

SUPERCOMPUTERSSystemNo photograph on file

gpu serverNew build72h burn-in36mo warranty

TF-8H100 HGX Node

Processors: 2x Intel Xeon Platinum 8480+
Accelerators: 8 x NVIDIA H100 SXM5 80GB
Cores: 112 total
Memory: 2TB DDR5
Storage: 8x 7.68TB U.2 NVMe
Fabric: 8x ConnectX-7 NDR400 + 2x 100GbE
Rack space: 8U
Peak power: 10.2kW · 44A at 230V
Heat rejected: 34,802 BTU/hr

8-way NVLink all-to-all, 900 GB/s per GPU
Delivered racked, cabled and burned in for 72 hours
10.2kW peak, three-phase and real cooling are prerequisites, not options

Ships with Ubuntu 22.04 LTS · NVIDIA driver + CUDA 12 · NVIDIA Container Toolkit · Slurm · NCCL tuned

Quoted per order

60 working days

Request a quote Full spec

None of these quite fits?

These are starting points, not a fixed menu. Open the configurator and change anything you like; the compatibility engine will hold you to what those changes cost in power, thermal budget and rack space.

Configure from scratch