NVIDIA GeForce RTX 2070 Super

NVIDIA8GB GDDR6PCIe Gen3Turing

Data updated 2026-11-04 15:09 UTC · refreshed every 5 min

Current Price

$0.10/hr

From $0.09/hr · lowest live offer

24 GPU · Good availability

Current Price

$0.10

+21.8% (24h)

Available Now

24 GPU

Good availability

Total in Network

34 GPU

Live data

Utilization

29.4%

Stable

Market history

Price Tracking

USD/hour (minimum · median)

Available GPUs

Ready to rent

Total in Network

Infrastructure Growth

Which LLMs run on one NVIDIA GeForce RTX 2070 Super

Open VRAM calculator with RTX 2070 Super

Estimated with our VRAM calculator for a single card: 8K context, 4 concurrent users, vLLM-style serving.

Largest that fitsINT4 / AWQ

Qwen3.5-4B

4B

6.6 of 8 GB83%

~62 tok/s per stream

Details

Where the memory goes

  • Model weights4.49 GB
  • KV cache1.07 GB
  • Activations0.02 GB
  • CUDA & framework1.02 GB
Precision
INT4 / AWQ
Serving preset
8K context × 4 users
Users at this context
9
Spare context in leftover VRAM
51K
Fit score
61/100 · High
Open in VRAM calculator
BalancedINT4 / AWQ

Llama 3.2 3B

3B

5.9 of 8 GB74%

~69 tok/s per stream

Details

Where the memory goes

  • Model weights2.29 GB
  • KV cache2.62 GB
  • Activations0.01 GB
  • CUDA & framework1.01 GB
Precision
INT4 / AWQ
Serving preset
8K context × 4 users
Users at this context
7
Spare context in leftover VRAM
49K
Fit score
68/100 · High
Open in VRAM calculator
CompactFP16

Qwen3.5-2B

2B

6.1 of 8 GB76%

~68 tok/s per stream

Details

Where the memory goes

  • Model weights4.60 GB
  • KV cache0.40 GB
  • Activations0.05 GB
  • CUDA & framework1.01 GB
Precision
FP16
Serving preset
8K context × 4 users
Users at this context
23
Spare context in leftover VRAM
125K
Fit score
66/100 · High
Open in VRAM calculator

Estimates, not benchmarks: real usage depends on the runtime, context and batch settings.

Technical Specifications

Memory

8GB GDDR6

FP32 Performance

9.1 TFLOPS

Tensor Performance

72.5 TFLOPS

Memory Bandwidth

448 GB/s

Architecture

Turing

TDP

215W

FP64 Performance

0.29 TFLOPS

CUDA Cores

2560

Tensor Cores

320

Ideal Use Cases

AI InferenceGaming3D Rendering

About NVIDIA GeForce RTX 2070 Super

The RTX 2070 Super offers enhanced Turing performance at a mid-range price point.

The NVIDIA GeForce RTX 2070 Super features 8GB of GDDR6 memory with 448 GB/s bandwidth, making it excellent for ai inference, gaming, 3d rendering. With 72.5 TFLOPS tensor performance and 9.1 TFLOPS FP32 compute, this NVIDIA Turing GPU delivers exceptional performance for demanding workloads.

Currently, 34 GPU RTX 2070 Super GPUs are available in the GPUniq network with 29.4% utilization. The average rental price is $0.10 per hour, with 24 GPU ready for immediate deployment.

RTX 2070 Super vs similar GPUs — specs & live rental prices

Prices are live minimum / median USD per hour on the GPUniq marketplace, as of 2026-11-04 15:09 UTC.

GPUVRAMArchitectureFP32TensorBandwidthTDPMin $/hrMedian $/hrAvailable
RTX 2070 Super8GB GDDR6Turing9.1 TFLOPS72.5 TFLOPS448 GB/s215W$0.09$0.1221
RTX 2080 Ti11GB GDDR6Turing13.4 TFLOPS107 TFLOPS616 GB/s250W$0.11$0.1641
RTX 20808GB GDDR6Turing10.1 TFLOPS80.5 TFLOPS448 GB/s215W$0.09$0.091
RTX 2060 Super8GB GDDR6Turing7.2 TFLOPS57.4 TFLOPS448 GB/s175W$0.08$0.1311

Frequently Asked Questions

How much does it cost to rent NVIDIA GeForce RTX 2070 Super?

The current rental price for NVIDIA GeForce RTX 2070 Super is $0.10 per hour on GPUniq. Prices may vary based on demand and availability.

What is NVIDIA GeForce RTX 2070 Super best used for?

NVIDIA GeForce RTX 2070 Super is ideal for AI Inference, Gaming, 3D Rendering. With 8GB of GDDR6 memory and 72.5 TFLOPS tensor performance, it excels at demanding AI and compute workloads.

How many NVIDIA GeForce RTX 2070 Super GPUs are available for rent?

Currently, there are 24 GPU available for immediate rental out of 34 GPU total in the GPUniq network. The current utilization is 29.4%.

Which LLMs can run on NVIDIA GeForce RTX 2070 Super?

On a single NVIDIA GeForce RTX 2070 Super, our VRAM calculator fits Qwen3.5-4B (INT4 / AWQ, 6.6 of 8 GB); Llama 3.2 3B (INT4 / AWQ, 5.9 of 8 GB); Qwen3.5-2B (FP16, 6.1 of 8 GB) — estimated at 8K context with 4 concurrent users.

What are the specifications of NVIDIA GeForce RTX 2070 Super?

NVIDIA GeForce RTX 2070 Super features 8GB GDDR6 memory, 9.1 TFLOPS FP32 performance, 72.5 TFLOPS tensor performance, 448 GB/s memory bandwidth, and 215W TDP. It uses the Turing architecture.

Related GPUs in GeForce RTX 20 Series

GPU rental guides

NVIDIA official specificationsAPI docsAbout GPUniqContact supportPrivacy policyTerms of use

$0.10/hr

RTX 2070 Super · 24 GPU

Rent now