Brand: AMD | Category: GPUs
SKU: AMD-100000001802 | Part #: 100-000001802 | MPN: 100-000001802
Contact for Pricing — Request a Quote
The AMD Instinct MI350X GPU Accelerator from AMD is enterprise-grade GPUs hardware built for data centers. Next-generation CDNA4 GPU accelerator delivering enhanced AI inference performance and power efficiency for large-scale enterprise deployments. Available in brand new condition. AMD gpus products are trusted by enterprises and data centers worldwide. Available from Omnixon Global. Contact our sales team to request a quote.
| Brand | AMD |
| Category | GPUs |
| SKU | AMD-100000001802 |
| Part Number | 100-000001802 |
| Condition | New |
| Model | Instinct MI350X |
| Architecture | CDNA4 |
| GPU Memory | 24 GB HBM3E |
| Memory Bandwidth | 960 GB/s |
| Peak FP8 Performance | 1.46 petaFLOPS (estimated) |
| Peak FP16 Performance | 728 teraFLOPS (estimated) |
| Peak TF32 Performance | 364 teraFLOPS (estimated) |
| Peak FP32 Performance | 182 teraFLOPS (estimated) |
| Tensor Engines | Architecture-optimized for mixed-precision inference |
| Compute Units | 240 CDNA4 cores |
| Infinity Fabric Interconnect | Yes, enhanced for multi-GPU scaling |
| PCIe Interface | PCIe 5.0 x16 |
| Thermal Design Power (TDP) | 410W (target efficiency improvement vs. MI325X) |
| Manufacturing Process | 5nm advanced node |
| Form Factor | Passive cooled accelerator card |
| Software Stack | ROCm 6.x and later compatible |
| Framework Support | PyTorch, TensorFlow, ONNX Runtime, vLLM, TensorRT-LLM |
| Launch Date | Q2 2025 |
| Target Application Class | Enterprise AI inference, large-scale model serving, inference optimization |