Data updated 2026-11-04 15:09 UTC · refreshed every 5 min
Current Price
$2.50
-0.3% (24h)
Available Now
49 GPU
Good availability
Total in Network
708 GPU
Live data
Utilization
93.1%
High
Market history
USD/hour (minimum · median)
Ready to rent
Infrastructure Growth
Estimated with our VRAM calculator for a single card: 8K context, 4 concurrent users, vLLM-style serving.
122B MoE · 10B active
~57 tok/s per stream
Where the memory goes
35B MoE · 3B active
~51 tok/s per stream
Where the memory goes
14B
~43 tok/s per stream
Where the memory goes
Estimates, not benchmarks: real usage depends on the runtime, context and batch settings.
Memory
96GB GDDR7
FP32 Performance
104.8 TFLOPS
Tensor Performance
3352 TFLOPS
Memory Bandwidth
1.79 TB/s
Architecture
Blackwell
TDP
350W
FP64 Performance
1.6 TFLOPS
CUDA Cores
21760
Tensor Cores
680
The NVIDIA RTX PRO 6000 is a professional workstation GPU with 96GB GDDR7 for demanding AI and visualization workloads.
The NVIDIA RTX PRO 6000 features 96GB of GDDR7 memory with 1.79 TB/s bandwidth, making it excellent for ai training, professional visualization, cad/cam. With 3352 TFLOPS tensor performance and 104.8 TFLOPS FP32 compute, this NVIDIA Blackwell GPU delivers exceptional performance for demanding workloads.
Currently, 708 GPU RTX PRO 6000 GPUs are available in the GPUniq network with 93.1% utilization. The average rental price is $2.50 per hour, with 49 GPU ready for immediate deployment.
The current rental price for NVIDIA RTX PRO 6000 is $2.50 per hour on GPUniq. Prices may vary based on demand and availability.
NVIDIA RTX PRO 6000 is ideal for AI Training, Professional Visualization, CAD/CAM, Scientific Computing, Content Creation. With 96GB of GDDR7 memory and 3352 TFLOPS tensor performance, it excels at demanding AI and compute workloads.
Currently, there are 49 GPU available for immediate rental out of 708 GPU total in the GPUniq network. The current utilization is 93.1%.
On a single NVIDIA RTX PRO 6000, our VRAM calculator fits Qwen3.5-122B-A10B (INT4 / AWQ, 75.3 of 96 GB); Qwen3.6 35B A3B (FP16, 82.4 of 96 GB); Qwen3-14B (FP16, 35.6 of 96 GB) — estimated at 8K context with 4 concurrent users.
NVIDIA RTX PRO 6000 features 96GB GDDR7 memory, 104.8 TFLOPS FP32 performance, 3352 TFLOPS tensor performance, 1.79 TB/s memory bandwidth, and 350W TDP. It uses the Blackwell architecture.
NVIDIA official specificationsAPI docsAbout GPUniqContact supportPrivacy policyTerms of use
$2.50/hr
RTX PRO 6000 · 49 GPU