Allocation openSpecial offer

SupermicroAMDLogos identify the maker. Blade AI is an independent supplier.

Live deal · AMD Instinct MI300X

Supermicro 8-GPU servers with AMD Instinct MI300X, about 6 to 8 weeks

Supermicro AS-8125GS-TNMR2 servers, each with eight AMD Instinct MI300X GPUs (192GB HBM3 each, 1.5TB of GPU memory per server), two AMD EPYC 9654 processors and 2.3TB of DDR5 in an 8U chassis, with 3 years of onsite next-business-day support. A proven AMD platform for large-model inference and training, about 6 to 8 weeks from order. Sold as complete servers only.

  • 8AMD Instinct MI300X GPUs per server, 192GB HBM3 each
  • 1.5TBGPU memory per server (an 8-GPU H200 server has 1.13TB)
  • 5.3TB/sMemory bandwidth per GPU (H200: 4.8)
  • 6 to 8 weeksFrom order, after compliance
Supermicro AS-8125GS-TNMR2 8U AMD Instinct MI300X GPU server, front three-quarter view

The lead-time gap

How fast this one ships

  1. AMD Instinct MI300X Supermicro 8-GPU servers, special offerSpecial offer
    Blade AI: 6–8 wks
    The market: 16–20 wks
    ~11 weeks sooner

The MI300X lead time runs from order, placed once end-user compliance clears. Confirmed on the quotation.

Specification

Specification of Supermicro 8-GPU servers with AMD Instinct MI300X, about 6 to 8 weeks
SystemSupermicro AS-8125GS-TNMR2, 8U GPU server
GPU8 x AMD Instinct MI300X, 192GB HBM3, 5.3TB/s each, on the AMD Instinct 8-GPU board
GPU memory, total1.5TB per server
Processors2 x AMD EPYC 9654
System memory2.3TB DDR5-5600
Storage1 x 1.9TB U.2 NVMe
Network4 x single-port 400GbE QSFP112, 1 x dual-port 10GbE RJ45
Expansion8 x PCIe 5.0 x16 low-profile + up to 4 x PCIe 5.0 x16 full-height slots
Power6 x 3000W redundant supplies (3+3), Titanium level
Cooling10 heavy-duty fans, air-cooled
Support3 years onsite next business day
Lead timeAbout 6 to 8 weeks from order, after end-user compliance clears
QuantityLimited quantity, subject to prior sale
PriceConfirmed on the quotation
  • End-of-life model, limited availability.
  • Sold as complete servers only, not as individual GPUs.
  • Offered subject to prior sale and end-user compliance. Specification, quantity and price are confirmed on the quotation.

How it compares

  • GPU memory: 192GB per MI300X against 141GB per H200, so 1.5TB per server against 1.13TB.
  • Bandwidth: 5.3TB/s per GPU against 4.8TB/s on H200. FP8: 2.6 PFLOPS per GPU dense.
  • Software: PyTorch, vLLM and SGLang run on AMD ROCm. For the newest models and FP4, look at the MI350X offer.

H200 or AMD? Read the comparison

Posted 13 November 2026. Specification as supplied. E&OE.

Proof before paymentSerial numbers and photos before the balance is due
Export checkedEnd-user screening on every order
Seller of recordYou pay the seller named on acceptance, never Blade AI

Other live deals

Register interest in this deal

Supermicro 8-GPU servers with AMD Instinct MI300X, about 6 to 8 weeks: Supermicro AS-8125GS-TNMR2. We reply within one working day with the quantity still open, the price and the lead time.

GPU systems are export-controlled. Before we quote we ask who the end user is and where the hardware will be installed. We do not supply the destinations listed on our export compliance page.

Blade AI Ltd · Registered in England and Wales, company 17424857 · VAT GB 531 6389 85 · D-U-N-S 235110576 · Every order export-screened

We reply within one working day. No sales queue.

Email Check availability