Data updated 2026-11-04 15:09 UTC · refreshed every 5 min
Current Price
$1.50
+15.0% (24h)
Available Now
100 GPU
High availability
Total in Network
589 GPU
Live data
Utilization
83.0%
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.
35B MoE · 3B active
~117 tok/s per stream
Where the memory goes
14B
~38 tok/s per stream
Where the memory goes
4B
~100 tok/s per stream
Where the memory goes
Estimates, not benchmarks: real usage depends on the runtime, context and batch settings.
Memory
40–80GB HBM2e
FP32 Performance
39 TFLOPS
Tensor Performance
624 TFLOPS
Memory Bandwidth
2.0 TB/s
Architecture
Ampere
TDP
400W
FP64 Performance
19.5 TFLOPS
CUDA Cores
6912
Tensor Cores
432
The NVIDIA A100 is a proven AI accelerator available in SXM4 and PCIe form factors, widely used for training large neural networks.
The NVIDIA A100 features 40–80GB of HBM2e memory with 2.0 TB/s bandwidth, making it excellent for ai training, deep learning, hpc. With 624 TFLOPS tensor performance and 39 TFLOPS FP32 compute, this NVIDIA Ampere GPU delivers exceptional performance for demanding workloads.
Currently, 589 GPU A100 GPUs are available in the GPUniq network with 83.0% utilization. The average rental price is $1.50 per hour, with 100 GPU ready for immediate deployment.
Prices are live minimum / median USD per hour on the GPUniq marketplace, as of 2026-11-04 15:09 UTC.
The current rental price for NVIDIA A100 is $1.50 per hour on GPUniq. Prices may vary based on demand and availability.
NVIDIA A100 is ideal for AI Training, Deep Learning, HPC, Scientific Research, Data Analytics. With 40–80GB of HBM2e memory and 624 TFLOPS tensor performance, it excels at demanding AI and compute workloads.
Currently, there are 100 GPU available for immediate rental out of 589 GPU total in the GPUniq network. The current utilization is 83.0%.
On a single NVIDIA A100, our VRAM calculator fits Qwen3.6 35B A3B (INT4 / AWQ, 23.8 of 40 GB); Qwen3-14B (FP16, 35.6 of 40 GB); Qwen3.5-4B (FP16, 11.4 of 40 GB) — estimated at 8K context with 4 concurrent users.
NVIDIA A100 features 40–80GB HBM2e memory, 39 TFLOPS FP32 performance, 624 TFLOPS tensor performance, 2.0 TB/s memory bandwidth, and 400W TDP. It uses the Ampere architecture.
NVIDIA official specificationsAPI docsAbout GPUniqContact supportPrivacy policyTerms of use
$1.50/hr
A100 · 100 GPU