Logos 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
The lead-time gap
How fast this one ships
-

AMD Instinct MI300X
Supermicro 8-GPU servers, special offerSpecial offer
Blade AI: 6–8 wksThe 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
| System | Supermicro AS-8125GS-TNMR2, 8U GPU server |
|---|---|
| GPU | 8 x AMD Instinct MI300X, 192GB HBM3, 5.3TB/s each, on the AMD Instinct 8-GPU board |
| GPU memory, total | 1.5TB per server |
| Processors | 2 x AMD EPYC 9654 |
| System memory | 2.3TB DDR5-5600 |
| Storage | 1 x 1.9TB U.2 NVMe |
| Network | 4 x single-port 400GbE QSFP112, 1 x dual-port 10GbE RJ45 |
| Expansion | 8 x PCIe 5.0 x16 low-profile + up to 4 x PCIe 5.0 x16 full-height slots |
| Power | 6 x 3000W redundant supplies (3+3), Titanium level |
| Cooling | 10 heavy-duty fans, air-cooled |
| Support | 3 years onsite next business day |
| Lead time | About 6 to 8 weeks from order, after end-user compliance clears |
| Quantity | Limited quantity, subject to prior sale |
| Price | Confirmed 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.
Other live deals
- MiTAC 8-GPU servers with AMD Instinct MI350X, available nowG8825Z5: 8 x AMD Instinct MI350X 288GB, 2 x EPYC 9575F, 3TB DDR5, 8 x 400G, 8U
- NVIDIA A100 GPU racks, complete systems, available nowZT Systems Gen 7.0 48U racks: 32 x A100 40GB SXM4 per rack, from a single rack
- Supermicro 10-GPU servers with AMD Instinct MI350P, available nowAS-5126GS-TNRT2: 10 x AMD Instinct MI350P 144GB, 2 x EPYC 9575F, 2TB DDR5-6400, 5U
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.
How a live deal works
- Register interest with the quantity, the site and the date you need it.
- We reply within one working day with the specification, the quantity still open and the price.
- Mutual NDA, then end-user and site documents for export screening. We may decline a deal.
- Your purchase order and deposit go to the seller of record. Serial numbers and photos reach you before the balance is due.
