Data updated 2026-11-04 17:39 UTC · refreshed every 5 min
Current Price
$0.11
+2.0% (24h)
Available Now
237 GPU
High availability
Total in Network
656 GPU
Live data
Utilization
63.9%
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.
8B
~35 tok/s per stream
Where the memory goes
4B
~42 tok/s per stream
Where the memory goes
2B
~57 tok/s per stream
Where the memory goes
Estimates, not benchmarks: real usage depends on the runtime, context and batch settings.
Memory
12GB GDDR6
FP32 Performance
12.7 TFLOPS
Tensor Performance
102 TFLOPS
Memory Bandwidth
360 GB/s
Architecture
Ampere
TDP
170W
FP64 Performance
0.19 TFLOPS
CUDA Cores
3584
Tensor Cores
112
The RTX 3060 offers 12GB of memory at an affordable price, popular for entry-level AI development.
The NVIDIA GeForce RTX 3060 features 12GB of GDDR6 memory with 360 GB/s bandwidth, making it excellent for ai inference, gaming, entry-level ml. With 102 TFLOPS tensor performance and 12.7 TFLOPS FP32 compute, this NVIDIA Ampere GPU delivers exceptional performance for demanding workloads.
Currently, 656 GPU RTX 3060 GPUs are available in the GPUniq network with 63.9% utilization. The average rental price is $0.11 per hour, with 237 GPU ready for immediate deployment.
Prices are live minimum / median USD per hour on the GPUniq marketplace, as of 2026-11-04 17:39 UTC.
| GPU | VRAM | Architecture | FP32 | Tensor | Bandwidth | TDP | Min $/hr | Median $/hr | Available |
|---|---|---|---|---|---|---|---|---|---|
| RTX 3060 | 12GB GDDR6 | Ampere | 12.7 TFLOPS | 102 TFLOPS | 360 GB/s | 170W | $0.06 | $0.11 | 216 |
| RTX 3090 Ti | 24GB GDDR6X | Ampere | 40 TFLOPS | 320 TFLOPS | 1.01 TB/s | 450W | $0.18 | $0.37 | 15 |
| RTX 3090 | 24GB GDDR6X | Ampere | 35.6 TFLOPS | 285 TFLOPS | 936 GB/s | 350W | $0.06 | $0.30 | 306 |
| RTX 3080 Ti | 12GB GDDR6X | Ampere | 34.1 TFLOPS | 273 TFLOPS | 912 GB/s | 350W | $0.15 | $0.30 | 166 |
The current rental price for NVIDIA GeForce RTX 3060 is $0.11 per hour on GPUniq. Prices may vary based on demand and availability.
NVIDIA GeForce RTX 3060 is ideal for AI Inference, Gaming, Entry-level ML, Content Creation. With 12GB of GDDR6 memory and 102 TFLOPS tensor performance, it excels at demanding AI and compute workloads.
Currently, there are 237 GPU available for immediate rental out of 656 GPU total in the GPUniq network. The current utilization is 63.9%.
On a single NVIDIA GeForce RTX 3060, our VRAM calculator fits Llama 3.1 8B (INT4 / AWQ, 9.8 of 12 GB); Qwen3.5-4B (FP8, 8.2 of 12 GB); Qwen3.5-2B (FP16, 6.1 of 12 GB) — estimated at 8K context with 4 concurrent users.
NVIDIA GeForce RTX 3060 features 12GB GDDR6 memory, 12.7 TFLOPS FP32 performance, 102 TFLOPS tensor performance, 360 GB/s memory bandwidth, and 170W TDP. It uses the Ampere architecture.
NVIDIA official specificationsAPI docsAbout GPUniqContact supportPrivacy policyTerms of use
$0.11/hr
RTX 3060 · 237 GPU