Rent NVIDIA RTX 2060 GPU by the hour
The NVIDIA RTX 2060 on ONIE is a Turing-architecture consumer GPU featuring 12 GB of VRAM and a 130 W TDP. It delivers about 6.5 TFLOPS of single-precision compute and about 268 GB/s of memory bandwidth with CUDA compute capability 7.5. Instances include SSH access, per-hour billing, and preconfigured templates for PyTorch/CUDA, ComfyUI, Ollama, and vLLM.
Specifications
VRAM per GPU
Architecture
Compute capability
FP32 compute
Memory bandwidth
Power limit
Values reported by the infrastructure provider for machines currently listed; real performance varies by machine.
Available configurations
Live stock and prices, updated continuously. The final price is confirmed before you order.
Loading live prices…
What the RTX 2060 is good for
Entry-Level Image Generation
Run ComfyUI workflows and standard diffusion models that fit comfortably within 12 GB of VRAM.
Compact Language Model Inference
Deploy quantized or smaller language models using Ollama or vLLM for lightweight text generation tasks.
PyTorch Prototyping and Debugging
Write, test, and debug CUDA code on a Turing architecture card before scaling up to larger instances.
Small-Scale Model Training
Train modest neural networks and machine learning pipelines using the PyTorch/CUDA template.
Is it the right GPU for you?
Choose the 12 GB RTX 2060 when your workload needs more memory than entry-level consumer cards offer, without requiring the higher compute throughput of newer architectures. Upgrade to a newer generation or workstation GPU for heavy training, or pick a smaller GPU if your task requires minimal VRAM.
Compare with similar GPUs
Frequently asked questions
Is the RTX 2060 suitable for LLM inference?
With 12 GB of VRAM and about 268 GB/s of memory bandwidth, it can handle compact and quantized language models via Ollama or vLLM. Larger models or high-throughput serving will require a GPU with more memory and higher bandwidth.
What software compatibility does the Turing architecture offer?
The RTX 2060 supports CUDA compute capability 7.5, which runs standard frameworks included in the PyTorch/CUDA template. Note that it lacks hardware support for certain newer data types introduced in later architectures.
How does this 12 GB RTX 2060 compare to other consumer GPUs?
The 12 GB memory capacity allows it to hold larger models and batch sizes than lower-memory consumer variants, though its about 6.5 TFLOPS of compute is more modest than newer-generation cards.
How do billing and instance access work on ONIE?
Instances are billed on a per-hour basis. You can connect directly via SSH or launch right into pre-configured templates for PyTorch/CUDA, vLLM, Ollama, and ComfyUI.
Rent the RTX 2060 by the hour
Create an account, choose a configuration and connect over SSH. Billing stops when you delete the GPU.
Rent RTX 2060