Rent an NVIDIA RTX 2070S GPU with 8 GB VRAM
Rent RTX 2070S cloud GPU servers by the hour on Cloudj: 8 GB VRAM on NVIDIA Turing with about 8.8 TFLOPS FP32 and 366 GB/s memory bandwidth. It is the fastest 8 GB Turing card in our list, good for developers running SD 1.5, quantized 7B LLMs and FP16 training tests at a 210 W power limit. Pick a live configuration, start from the Ubuntu 22.04 + CUDA or PyTorch + JupyterLab template and connect over SSH with your key.
RTX 2070S specifications
VRAM per GPU
8 GB
Architecture
NVIDIA Turing
Compute capability
7.5
FP32 compute
≈ 8.8 TFLOPS
Memory bandwidth
≈ 366 GB/s
Power limit
210 W
Values reported by the infrastructure provider for machines currently listed; real performance varies by machine.
Live RTX 2070S configurations and prices
From $0.15/h
incl. 32 GB disk · Live price, updated every 15 minutes
What you can run on the RTX 2070S cloud GPU
Faster SD 1.5 batches
8.8 TFLOPS FP32 and Tensor Cores speed up Stable Diffusion 1.5 batches in ComfyUI.
7B models at 4-bit
Serve quantized 7B–8B models in Ollama for testing apps and prompts.
CUDA and TensorRT testing
Build and benchmark inference code on Turing (compute capability 7.5) in a clean server.
Small model training
Train compact vision or audio models with FP16 mixed precision.
Is the RTX 2070S the right GPU for your workload?
Choose the RTX 2070S for development, debugging, and lightweight inference tasks that fit within 8 GB of VRAM. Move to a GPU with more memory and higher compute capability for training large models, or pick a lower-power consumer card for basic script testing.
Guides for RTX 2070S
RTX 2070S cloud GPU: frequently asked questions
Rent the RTX 2070S cloud GPU by the hour
Pick a live configuration, choose a template and connect over SSH with your key. Billing stops when you destroy the instance.