NVIDIA RTX PRO 6000 Blackwell Server Edition
Datacenter
VRAM
96 GB
Memory
GDDR7 ECC
Bandwidth
1597 GB/s
TDP
600W
Suitable Workloads
Large Language Models
Training and inference for models like GPT-4, Llama 70B+
Deep Learning Training
High-performance training for neural networks
Enterprise Deployment
Designed for 24/7 datacenter operations
Key Highlights
- Built on Blackwell architecture
- 24,064 compute cores for parallel processing
- PCIe form factor
Memory
VRAM96 GB
Memory TypeGDDR7 ECC
Memory Bandwidth1597 GB/s
Compute Performance
FP32 (Single Precision)120 TFLOPS
FP16 (Half Precision)1000 TFLOPS
BF161000 TFLOPS
Architecture
ArchitectureBlackwell
Compute Cores24,064
Release Year2025
Power & Physical
TDP600 W
Form FactorPCIe
PCIe GenerationPCIe 5.0
Notes
Passive dual-slot server variant. FP4 4 PF / FP8 2 PF / FP16 1 PF dense per NVIDIA datasheet. Popular single-card inference option in 1U/2U racks.
Models That May Fit on NVIDIA RTX PRO 6000 Blackwell Server Edition
Estimates based on INT8 quantization. Actual fit depends on framework and batch size.
Explore More
Added Jul 30, 2026
Last updated: Jul 30, 2026
Your AI stack shouldn't stand still.
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.