EstimatesHardware prices change daily, so prices here are estimates. Add what you need to your basket and request your final price: we reply within one working day.
Supermicro · SKU WSL-5126GS-TNRT2-4XR6000

Supermicro A+ Server AS-5126GS-TNRT2 — 2× EPYC 9555, 4× RTX PRO 6000 Blackwell Server Edition

5U 10-GPU-capable server: 2× AMD EPYC 9555 (128 cores), 1.5 TB DDR5-6400 ECC, 4× RTX PRO 6000 Blackwell Server Edition (384 GB), dual 100GbE.

estimate · ex VAT
£177,485.74
£212,982.89 inc VAT
Lead time 3 weeksestimate — final price on enquiry

Members pay £176,985.74 for this (ex VAT; £212,382.89 inc VAT). Join for £75 + VAT/month and take £500 off today — membership's more than half paid for before it ships.

Join & save £500
  • 60-day price lock for members
  • Engineer on the phone, Mon–Fri 9–6
  • 30-day returns (60 for members)

Ex VAT, at basket checkout. Terms

Specifications
OSUbuntu 24.04 LTS Server
ManagementSupermicro Server Manager (SSM), TPM 2.0
ModelSupermicro A+ Server AS-5126GS-TNRT2
Power2700 W (4+2) redundant; 6× C14–C19 power cables
Form factor5U rackmount, up to 10 GPUs, 10× 2.5" hot-swap bays
Boot storage960 GB Samsung PM9A3 M.2 NVMe
NetworkingBroadcom P2100G dual 100GbE (QSFP56); AIOM dual 10GbE RJ45 (Intel X710-AT2)
Data storage2× 7.68 TB Solidigm D7-PS1010 U.2 PCIe 5.0 NVMe
GPUs4× NVIDIA RTX PRO 6000 Blackwell Server Edition, 96 GB GDDR7 each (384 GB), PCIe 5.0 x16, passive
Memory1.5 TB DDR5-6400 ECC RDIMM (24× 64 GB)
Warranty3-year depot
CPUs2× AMD EPYC 9555 (64 cores, 3.2 GHz, 256 MB cache, 360 W)

Your build

estimate — final price on enquiry
£177,485.74
ex VAT
VAT—
Total inc VAT£212,982.89

Lead time 3 weeks1
Will it run?

Check a model against our machines before you buy.

Pick the model and quantisation you plan to run. We'll show whether it fits in memory, how much room is left for context, and the throughput to expect. Estimates come from memory bandwidth and are replaced by our own bench figures where we have them.

Machine

Quantisation

Tokens of context you'll actually use16k
Fits
Llama 3.3 70B at Q4_K_M runs on the DGX Spark
16k context · 128 GB available · bandwidth estimate
Needs
58 GB
Headroom
+70 GB
Est. speed
3.8 tok/s · est.

Comfortable. 70 GB spare — room for 128k context, a second small model, or a RAG index in memory. Expect roughly 3.8 tok/s single-stream.

Machines that run this configuration

Not sure? Book a free 20-minute sizing call

Weights 42.8 GB at 4.85 bits/param · KV cache 5.0 GB at 16k (fp16, approximate) · 10 GB reserved for OS and runtime. Speed is single-stream decode, memory-bound; prompt processing and batching behave differently. Members: £5,099 on this machine. Or WhatsApp an engineer on .

A 5U GPU server with room to grow: it ships with four NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs (384 GB of VRAM) and takes up to ten, so an inference or fine-tuning cluster node can start at four and expand. Built to order and burned in before dispatch.

  • 2× AMD EPYC 9555, 64 cores each, 3.2 GHz, 256 MB cache (360 W)
  • 1.5 TB DDR5-6400 ECC RDIMM (24× 64 GB)
  • 4× NVIDIA RTX PRO 6000 Blackwell Server Edition, 96 GB GDDR7 each, passive (10 GPU slots)
  • 960 GB Samsung PM9A3 M.2 NVMe (OS) + 2× 7.68 TB Solidigm D7-PS1010 U.2 PCIe 5.0 NVMe; 10× 2.5" hot-swap bays
  • Broadcom P2100G dual 100GbE QSFP56 + AIOM dual 10GbE (Intel X710-AT2)
  • 2700 W (4+2) redundant power, TPM 2.0, Supermicro Server Manager
  • Ubuntu 24.04 LTS Server, 3-year depot warranty
Supermicro A+ Server AS-5126GS-TNRT2 — 2× EPYC 9555, 4× RTX PRO 6000 Blackwell Server Edition · Workstation AI Shop