Data updated 2026-11-04 15:09 UTC · refreshed every 5 min
Current Price
$0.17
-3.3% (24h)
Available Now
24 GPU
Good availability
Total in Network
107 GPU
Live data
Utilization
77.6%
Stable
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.
4B
~62 tok/s per stream
Where the memory goes
3B
~57 tok/s per stream
Where the memory goes
2B
~68 tok/s per stream
Where the memory goes
Estimates, not benchmarks: real usage depends on the runtime, context and batch settings.
Memory
8GB GDDR7
FP32 Performance
18.9 TFLOPS
Tensor Performance
605 TFLOPS
Memory Bandwidth
336 GB/s
Architecture
Blackwell
TDP
150W
FP64 Performance
0.3 TFLOPS
CUDA Cores
3840
Tensor Cores
120
The RTX 5060 is the most affordable Blackwell GPU for entry-level AI and gaming workloads.
The NVIDIA GeForce RTX 5060 features 8GB of GDDR7 memory with 336 GB/s bandwidth, making it excellent for ai inference, gaming, content creation. With 605 TFLOPS tensor performance and 18.9 TFLOPS FP32 compute, this NVIDIA Blackwell GPU delivers exceptional performance for demanding workloads.
Currently, 107 GPU RTX 5060 GPUs are available in the GPUniq network with 77.6% utilization. The average rental price is $0.17 per hour, with 24 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.
| GPU | VRAM | Architecture | FP32 | Tensor | Bandwidth | TDP | Min $/hr | Median $/hr | Available |
|---|---|---|---|---|---|---|---|---|---|
| RTX 5060 | 8GB GDDR7 | Blackwell | 18.9 TFLOPS | 605 TFLOPS | 336 GB/s | 150W | $0.10 | $0.16 | 48 |
| RTX 5090 | 32GB GDDR7 | Blackwell | 104.8 TFLOPS | 3352 TFLOPS | 1.79 TB/s | 575W | $0.51 | $1.20 | 454 |
| RTX 5080 | 16GB GDDR7 | Blackwell | 63.6 TFLOPS | 2036 TFLOPS | 960 GB/s | 360W | $0.28 | $0.51 | 221 |
| RTX 5070 Ti | 16GB GDDR7 | Blackwell | 48.6 TFLOPS | 1556 TFLOPS | 896 GB/s | 300W | $0.24 | $0.45 | 334 |
The current rental price for NVIDIA GeForce RTX 5060 is $0.17 per hour on GPUniq. Prices may vary based on demand and availability.
NVIDIA GeForce RTX 5060 is ideal for AI Inference, Gaming, Content Creation, Entry-level ML. With 8GB of GDDR7 memory and 605 TFLOPS tensor performance, it excels at demanding AI and compute workloads.
Currently, there are 24 GPU available for immediate rental out of 107 GPU total in the GPUniq network. The current utilization is 77.6%.
On a single NVIDIA GeForce RTX 5060, our VRAM calculator fits Qwen3.5-4B (INT4 / AWQ, 6.6 of 8 GB); Llama 3.2 3B (FP8, 7.2 of 8 GB); Qwen3.5-2B (FP16, 6.1 of 8 GB) — estimated at 8K context with 4 concurrent users.
NVIDIA GeForce RTX 5060 features 8GB GDDR7 memory, 18.9 TFLOPS FP32 performance, 605 TFLOPS tensor performance, 336 GB/s memory bandwidth, and 150W TDP. It uses the Blackwell architecture.
NVIDIA official specificationsAPI docsAbout GPUniqContact supportPrivacy policyTerms of use
$0.17/hr
RTX 5060 · 24 GPU