NVIDIA GeForce RTX 4070 Ti Super

NVIDIA16GB GDDR6XPCIe Gen4Ada Lovelace

Data updated 2026-11-04 15:10 UTC · refreshed every 5 min

Current Price

$0.35/hr

From $0.19/hr · lowest live offer

115 GPU · High availability

Current Price

$0.35

-3.9% (24h)

Available Now

115 GPU

High availability

Total in Network

222 GPU

Live data

Utilization

48.2%

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 4070 Ti Super

Open VRAM calculator with RTX 4070 Ti Super

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

Largest that fitsINT4 / AWQ

GPT-OSS 20B

21B MoE · 3.6B active

14.2 of 16 GB89%

~57 tok/s per stream

Details

Where the memory goes

  • Model weights12.24 GB
  • KV cache0.82 GB
  • Activations0.02 GB
  • CUDA & framework1.12 GB
Precision
INT4 / AWQ
Serving preset
8K context × 4 users
Users at this context
12
Spare context in leftover VRAM
41K
Fit score
56/100 · High
Open in VRAM calculator
BalancedINT4 / AWQ

Qwen3.5-9B

9B

10.8 of 16 GB68%

~55 tok/s per stream

Details

Where the memory goes

  • Model weights8.68 GB
  • KV cache1.07 GB
  • Activations0.03 GB
  • CUDA & framework1.05 GB
Precision
INT4 / AWQ
Serving preset
8K context × 4 users
Users at this context
23
Spare context in leftover VRAM
142K
Fit score
73/100 · Moderate
Open in VRAM calculator
CompactFP16

Qwen3.5-4B

4B

11.4 of 16 GB71%

~52 tok/s per stream

Details

Where the memory goes

  • Model weights9.20 GB
  • KV cache1.07 GB
  • Activations0.06 GB
  • CUDA & framework1.02 GB
Precision
FP16
Serving preset
8K context × 4 users
Users at this context
21
Spare context in leftover VRAM
126K
Fit score
70/100 · High
Open in VRAM calculator

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

Technical Specifications

Memory

16GB GDDR6X

FP32 Performance

44.1 TFLOPS

Tensor Performance

706 TFLOPS

Memory Bandwidth

672 GB/s

Architecture

Ada Lovelace

TDP

285W

FP64 Performance

0.7 TFLOPS

CUDA Cores

8448

Tensor Cores

264

Ideal Use Cases

Machine LearningAI Inference3D RenderingVideo EditingGaming

About NVIDIA GeForce RTX 4070 Ti Super

The RTX 4070 Ti Super offers great mid-range performance for AI and creative workloads.

The NVIDIA GeForce RTX 4070 Ti Super features 16GB of GDDR6X memory with 672 GB/s bandwidth, making it excellent for machine learning, ai inference, 3d rendering. With 706 TFLOPS tensor performance and 44.1 TFLOPS FP32 compute, this NVIDIA Ada Lovelace GPU delivers exceptional performance for demanding workloads.

Currently, 222 GPU RTX 4070 Ti Super GPUs are available in the GPUniq network with 48.2% utilization. The average rental price is $0.35 per hour, with 115 GPU ready for immediate deployment.

RTX 4070 Ti 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 15:10 UTC.

GPUVRAMArchitectureFP32TensorBandwidthTDPMin $/hrMedian $/hrAvailable
RTX 4070 Ti Super16GB GDDR6XAda Lovelace44.1 TFLOPS706 TFLOPS672 GB/s285W$0.20$0.36120
RTX 409024GB GDDR6XAda Lovelace82.6 TFLOPS1321 TFLOPS1.01 TB/s450W$0.36$0.76295
RTX 4080 Super16GB GDDR6XAda Lovelace52.2 TFLOPS836 TFLOPS736 GB/s320W$0.21$0.3570
RTX 408016GB GDDR6XAda Lovelace48.7 TFLOPS780 TFLOPS717 GB/s320W$0.25$0.3819

Frequently Asked Questions

How much does it cost to rent NVIDIA GeForce RTX 4070 Ti Super?

The current rental price for NVIDIA GeForce RTX 4070 Ti Super is $0.35 per hour on GPUniq. Prices may vary based on demand and availability.

What is NVIDIA GeForce RTX 4070 Ti Super best used for?

NVIDIA GeForce RTX 4070 Ti Super is ideal for Machine Learning, AI Inference, 3D Rendering, Video Editing, Gaming. With 16GB of GDDR6X memory and 706 TFLOPS tensor performance, it excels at demanding AI and compute workloads.

How many NVIDIA GeForce RTX 4070 Ti Super GPUs are available for rent?

Currently, there are 115 GPU available for immediate rental out of 222 GPU total in the GPUniq network. The current utilization is 48.2%.

Which LLMs can run on NVIDIA GeForce RTX 4070 Ti Super?

On a single NVIDIA GeForce RTX 4070 Ti Super, our VRAM calculator fits GPT-OSS 20B (INT4 / AWQ, 14.2 of 16 GB); Qwen3.5-9B (INT4 / AWQ, 10.8 of 16 GB); Qwen3.5-4B (FP16, 11.4 of 16 GB) — estimated at 8K context with 4 concurrent users.

What are the specifications of NVIDIA GeForce RTX 4070 Ti Super?

NVIDIA GeForce RTX 4070 Ti Super features 16GB GDDR6X memory, 44.1 TFLOPS FP32 performance, 706 TFLOPS tensor performance, 672 GB/s memory bandwidth, and 285W TDP. It uses the Ada Lovelace architecture.

Related GPUs in GeForce RTX 40 Series

GPU rental guides

NVIDIA official specificationsAPI docsAbout GPUniqContact supportPrivacy policyTerms of use

$0.35/hr

RTX 4070 Ti Super · 115 GPU

Rent now