AMD Instinct MI350X vs NVIDIA GeForce RTX 5080 — Comparaison GPU (Jun 2026)
AMD Instinct MI350X (288GB HBM3e, 1,800 TFLOPS FP16, CDNA 4) vs NVIDIA GeForce RTX 5080 (16GB GDDR7, 56 TFLOPS FP16, Blackwell)
|
AMD Instinct MI350X
288GB HBM3e · CDNA 4
|
NVIDIA GeForce RTX 5080
16GB GDDR7 · Blackwell
|
||
|---|---|---|---|
| Spécifications | |||
| Fabricant | AMD | NVIDIA | |
| Architecture | CDNA 4 | Blackwell | |
| VRAM | 288 GB HBM3e | 16 GB GDDR7 | |
| Bande passante | 8,000 GB/s | 960 GB/s | |
| FP16 (Tensor) | 1800.0 TFLOPS | 56.0 TFLOPS | |
| FP32 | 72.0 TFLOPS | 28.0 TFLOPS | |
| TDP | 1000W | 360W | |
| Année de sortie | 2025 | 2025 | |
| Segment | Centre de données | GPUs grand public | |
| Idéal pour | Next-gen AI training inference at scale | Gaming inference fine-tuning | |
| Tarification Cloud | |||
| Le moins cher à la demande | — | — | |
| Le moins cher en Spot | — | — | |
| Fournisseurs | 1 | 0 | |
AMD Instinct MI350X
NVIDIA GeForce RTX 5080