
Current flagship (2024-2025)
NVIDIA
Blackwell
NVIDIA Blackwell is the current flagship GPU architecture, featuring HBM3e memory with up to 8.0 TB/s bandwidth, NVLink 5 interconnects (1.8 TB/s), and 2.5× faster performance than H100 for LLM workloads. Available in configurations up to 288GB VRAM.
GPU Models in this Family
Click any card to expand detailed specifications

GB300 NVL72
13,824 GB HBM3e (192 GB per GPU × 72)8.0 TB/s per GPUNVL72 rack (72 GPUs)

GB300 NVL72
NVIDIA's flagship rack-scale AI system with 72 Blackwell Ultra GPUs. Designed for trillion-parameter model training.

B300
288 GB HBM3e8.0 TB/sSXM (dual-die)

B300
Blackwell Ultra standalone GPU. 288GB HBM3e — 1.5× more VRAM than B200. Flagship for extreme-scale AI training.

GB200 NVL72
13,824 GB HBM3e (192 GB per GPU × 72)8.0 TB/s per GPUNVL72 rack (72 GPUs)

GB200 NVL72
NVIDIA's flagship rack-scale AI system with 72 Blackwell GPUs and 36 Grace CPUs. Designed for trillion-parameter model training.

B200
192 GB HBM3e8.0 TB/sSXM (HGX) / PCIe (B200 NVL)

B200
NVIDIA B200 Blackwell flagship accelerator. Available in two form factors: SXM for highest power density (1000W, used in HGX B200 baseboards with NVLink 5), and PCIe as B200 NVL for traditional air-cooled server chassis (800W). Features 192 GB HBM3e memory with 8.0 TB/s bandwidth. 2.5× faster AI training than H100.

B100
192 GB HBM3e8.0 TB/sSXM (dual-die)

B100
Entry-level Blackwell GPU. Lower power variant of B200 for mainstream AI workloads.

RTX PRO 6000 Blackwell
96 GB GDDR71,792 GB/sPCIe Gen5 / SXM

RTX PRO 6000 Blackwell
Professional workstation/datacenter GPU based on Blackwell architecture. 96GB GDDR7 for AI, rendering, and graphics workloads.

RTX PRO 6000 SE
96 GB GDDR71,792 GB/sPCIe Gen5

RTX PRO 6000 SE
Server Edition of RTX PRO 6000 Blackwell. 96GB GDDR7. Optimized for datacenter deployment with lower TDP (300W PCIe).

GB200
192 GB HBM3e8.0 TB/sSuperchip (Grace CPU + Blackwell GPU)

GB200
Grace + Blackwell superchip with unified memory. The foundation of the GB200 NVL72 rack system.
Quick Comparison
| GPU Model | VRAM | Bandwidth | FP16 | TDP | Starting Price |
|---|---|---|---|---|---|
| GB300 NVL72 | 13,824 GB HBM3e (192 GB per GPU × 72) | 8.0 TB/s per GPU | 1.1 ExaFLOPS (rack-level) | TBD | — |
| B300 | 288 GB HBM3e | 8.0 TB/s | 2,500 TFLOPS (with sparsity) | 1,200W | — |
| GB200 NVL72 | 13,824 GB HBM3e (192 GB per GPU × 72) | 8.0 TB/s per GPU | 720 PFLOPS (rack-level) | 1,000W per GPU | — |
| B200 | 192 GB HBM3e | 8.0 TB/s | 2,250 TFLOPS (with sparsity) | 1000W (SXM) / 800W (NVL) | — |
| B100 | 192 GB HBM3e | 8.0 TB/s | 1,800 TFLOPS (with sparsity) | 700W | — |
| RTX PRO 6000 Blackwell | 96 GB GDDR7 | 1,792 GB/s | 1,250 TFLOPS (with sparsity) | 600W (SXM), 300W (PCIe) | — |
| RTX PRO 6000 SE | 96 GB GDDR7 | 1,792 GB/s | 1,250 TFLOPS (with sparsity) | 300W | — |
| GB200 | 192 GB HBM3e | 8.0 TB/s | 1,800 TFLOPS (with sparsity) | 1,000W | — |
Why Choose Blackwell?
Proven Performance
Blackwell GPUs power the world's largest AI training clusters. Battle-tested in production at scale for LLM training, fine-tuning, and inference.
Cloud-Native Ready
Available across multiple cloud providers with hourly billing. Compare real-time pricing and pick the cheapest option for your workload.
Ecosystem Support
Full compatibility with PyTorch, TensorFlow, JAX, vLLM, TensorRT, and all major ML frameworks. NVLink for multi-GPU scaling.