AMD Instinct MI350X
Air-cooled CDNA 4 accelerator with 288 GB of HBM3e and 8 TB/s of memory bandwidth, designed for retrofit into existing MI300/MI325 OAM platforms. New native FP4 and FP6 datatypes target inference cost-per-token reductions over Hopper-class hardware.
VRAM
288 GB
Memory
HBM3e
Bandwidth
8000 GB/s
TDP
1000W
Suitable Workloads
Large Language Models
Training and inference for models like GPT-4, Llama 70B+
Deep Learning Training
High-performance training for neural networks
Distributed Training
Multi-node training with fast interconnects
High-Throughput Inference
Optimized for batched inference workloads
Key Highlights
- Built on CDNA 4 architecture
- OAM form factor
Memory
Compute Performance
Architecture
Power & Physical
Interconnect
Notes
Spec verification recommended: numbers reflect AMD's Advancing AI 2025 announcement; double-check against the published MI350X datasheet before relying for production sizing.
Models That May Fit on AMD Instinct MI350X
Estimates based on INT8 quantization. Actual fit depends on framework and batch size.
Explore More
Added Apr 30, 2026
Last updated: Apr 30, 2026
Start building with the right model.
From model selection to production, one platform, no fragmentation.