← Back to all offerings

T4

16 GB VRAM65 FP16 TFLOPS70 W TDP7 providers603 offerings91 regions

The T4 is a cloud GPU with 16 GB of memory and 70 W TDP. It is currently available from 7 providers starting at $0.17/hr, with a market median of $1.41/hr across 603 offerings.

$0.17/hr
Cheapest
on Alibaba Cloud GPU
$1.41/hr
Median
across 603 offerings
$9.33/hr
Most expensive
+30.6%
90-day trend

Best deal

Hardware specifications

Architecture
Turing
VRAM
16 GB
Memory bandwidth
300 GB/s
FP16
65 TFLOPS
FP32
8 TFLOPS
TDP
70 W

Same across all providers.

Market comparison

$1.41/hr
Our median / hr
$0.20/hr
gpus.io median / hr
603
Our providers
3
gpus.io providers

View source on gpus.io

All-time price history

Offerings

All ×N×1×2×4×8In stock only · Partners only
ProviderCloudCountvCPURAMRegionPer GPU hrSPOTTotal/hr
Alibaba Cloud GPU
0.0% 30dReferral link
×2186 GBus-east-1$0.32/hr$0.63/hrLaunch ↗
Alibaba Cloud GPU
0.0% 30dReferral link
×2186 GBus-west-1$0.33/hr$0.65/hrLaunch ↗
Alibaba Cloud GPU
0.0% 30dReferral link
×2186 GBcn-hongkong$0.33/hr$0.66/hrLaunch ↗
Alibaba Cloud GPU
0.0% 30dReferral link
×2186 GBap-southeast-5$0.35/hr$0.69/hrLaunch ↗
Alibaba Cloud GPU
0.0% 30dReferral link
×2186 GBap-northeast-1$0.35/hr$0.70/hrLaunch ↗
Alibaba Cloud GPU
0.0% 30dReferral link
×2186 GBcn-zhangjiakou$0.36/hr$0.71/hrLaunch ↗
Alibaba Cloud GPU
0.0% 30dReferral link
×2186 GBcn-wulanchabu$0.36/hr$0.71/hrLaunch ↗
Alibaba Cloud GPU
0.0% 30dReferral link
×2186 GBcn-chengdu$0.36/hr$0.71/hrLaunch ↗
Alibaba Cloud GPU
0.0% 30dReferral link
×2186 GBeu-central-1$0.36/hr$0.72/hrLaunch ↗
Alibaba Cloud GPU
0.0% 30dReferral link
×2186 GBap-southeast-3$0.37/hr$0.73/hrLaunch ↗
Alibaba Cloud GPU
0.0% 30dReferral link
×2186 GBap-southeast-1$0.37/hr$0.74/hrLaunch ↗
Alibaba Cloud GPU
0.0% 30dReferral link
×2186 GBcn-hangzhou$0.40/hr$0.79/hrLaunch ↗
Alibaba Cloud GPU
0.0% 30dReferral link
×2186 GBcn-qingdao$0.40/hr$0.79/hrLaunch ↗
Alibaba Cloud GPU
0.0% 30dReferral link
×2186 GBcn-shanghai$0.40/hr$0.79/hrLaunch ↗
Alibaba Cloud GPU
0.0% 30dReferral link
×2186 GBcn-beijing$0.40/hr$0.79/hrLaunch ↗
Alibaba Cloud GPU
0.0% 30dReferral link
×2186 GBcn-heyuan$0.40/hr$0.79/hrLaunch ↗
Alibaba Cloud GPU
0.0% 30dReferral link
×2186 GBcn-guangzhou$0.40/hr$0.79/hrLaunch ↗
Alibaba Cloud GPU
0.0% 30dReferral link
×2186 GBcn-shenzhen$0.40/hr$0.79/hrLaunch ↗
Alibaba Cloud GPU
0.0% 30dReferral link
×2186 GBme-central-1$0.45/hr$0.89/hrLaunch ↗
Naver Cloud GPU
0.0% 30dReferral link
×240 GBkr-seoul$0.52/hr$1.03/hrLaunch ↗
Naver Cloud GPU
0.0% 30dReferral link
×240 GBkr-seoul$0.52/hr$1.03/hrLaunch ↗
Naver Cloud GPU
0.0% 30dReferral link
×240 GBkr-seoul$0.52/hr$1.03/hrLaunch ↗
Naver Cloud GPU
0.0% 30dReferral link
×240 GBkr-seoul$0.52/hr$1.04/hrLaunch ↗
Naver Cloud GPU
0.0% 30dReferral link
×280 GBkr-seoul$0.70/hr$1.40/hrLaunch ↗
Naver Cloud GPU
0.0% 30dReferral link
×280 GBkr-seoul$0.70/hr$1.40/hrLaunch ↗
Naver Cloud GPU
0.0% 30dReferral link
×280 GBkr-seoul$0.70/hr$1.40/hrLaunch ↗
Naver Cloud GPU
0.0% 30dReferral link
×280 GBkr-seoul$0.70/hr$1.40/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBla-south-2$0.75/hr$1.50/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBla-north-2$0.75/hr$1.50/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBla-south-2$0.75/hr$1.50/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBna-mexico-1$0.75/hr$1.50/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBla-north-2$0.75/hr$1.50/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBna-mexico-1$0.75/hr$1.50/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBeu-west-101$0.80/hr$1.59/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBeu-west-101$0.80/hr$1.59/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBeu-west-0$0.87/hr$1.73/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBme-east-1$0.92/hr$1.84/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBme-east-1$0.92/hr$1.84/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBmy-kualalumpur-1$1.00/hr$2.00/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBap-southeast-3$1.00/hr$2.00/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBap-southeast-2$1.00/hr$2.00/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBap-southeast-2$1.00/hr$2.00/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBap-southeast-3$1.00/hr$2.00/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBmy-kualalumpur-1$1.00/hr$2.00/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBcn-southwest-2$1.04/hr$2.07/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBcn-southwest-2$1.04/hr$2.07/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBcn-east-2$1.05/hr$2.09/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBcn-east-2$1.05/hr$2.09/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBcn-south-1$1.05/hr$2.09/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBcn-north-4$1.05/hr$2.09/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBcn-east-3$1.05/hr$2.09/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBcn-east-3$1.05/hr$2.09/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBcn-south-1$1.05/hr$2.09/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBcn-north-4$1.05/hr$2.09/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBaf-south-1$1.05/hr$2.10/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBaf-south-1$1.05/hr$2.10/hrLaunch ↗
Naver Cloud GPU
0.0% 30dReferral link
×2160 GBkr-seoul$1.06/hr$2.12/hrLaunch ↗
Naver Cloud GPU
0.0% 30dReferral link
×2160 GBkr-seoul$1.07/hr$2.13/hrLaunch ↗
Naver Cloud GPU
0.0% 30dReferral link
×2160 GBkr-seoul$1.07/hr$2.13/hrLaunch ↗
Naver Cloud GPU
0.0% 30dReferral link
×2160 GBkr-seoul$1.07/hr$2.13/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBsa-brazil-1$1.15/hr$2.30/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBsa-brazil-1$1.15/hr$2.30/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBap-southeast-1$1.16/hr$2.32/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×264 GBap-southeast-1$1.16/hr$2.32/hrLaunch ↗
Tencent Cloud GPU
0.0% 30dReferral link
×2160 GBna-ashburn-2$1.32/hr$2.63/hrLaunch ↗
Tencent Cloud GPU
0.0% 30dReferral link
×2226 GBap-nanjing-1$1.43/hr$2.85/hrLaunch ↗
Tencent Cloud GPU
0.0% 30dReferral link
×2226 GBap-beijing-6$1.43/hr$2.85/hrLaunch ↗
Tencent Cloud GPU
0.0% 30dReferral link
×2384 GBap-beijing-7$1.44/hr$2.87/hrLaunch ↗
Tencent Cloud GPU
0.0% 30dReferral link
×2160 GBap-seoul-2$1.47/hr$2.94/hrLaunch ↗
Tencent Cloud GPU
0.0% 30dReferral link
×2160 GBap-bangkok-2$1.86/hr$3.71/hrLaunch ↗
Tencent Cloud GPU
0.0% 30dReferral link
×2160 GBap-nanjing-3$2.07/hr$4.13/hrLaunch ↗
Tencent Cloud GPU
0.0% 30dReferral link
×2160 GBap-nanjing-1$2.07/hr$4.13/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×2504 GBla-south-2$2.39/hr$4.78/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×2504 GBla-south-2$2.39/hr$4.78/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×2504 GBcn-southwest-2$2.41/hr$4.82/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×2504 GBcn-southwest-2$2.41/hr$4.82/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×2504 GBcn-east-3$2.56/hr$5.11/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×2504 GBcn-east-3$2.56/hr$5.11/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×2504 GBcn-north-4$2.56/hr$5.11/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×2504 GBcn-south-1$2.56/hr$5.11/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×2504 GBcn-south-1$2.56/hr$5.11/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×2504 GBcn-north-4$2.56/hr$5.11/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×2560 GBcn-south-1$2.91/hr$5.82/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×2504 GBap-southeast-1$3.38/hr$6.75/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×2504 GBap-southeast-1$3.38/hr$6.75/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×2504 GBme-east-1$3.45/hr$6.89/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×2504 GBme-east-1$3.45/hr$6.89/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×2504 GBap-southeast-3$3.76/hr$7.52/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×2504 GBap-southeast-3$3.76/hr$7.52/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×2504 GBap-southeast-3$3.76/hr$7.52/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×2504 GBap-southeast-3$3.76/hr$7.52/hrLaunch ↗
Tencent Cloud GPU
0.0% 30dReferral link
×2160 GBap-nanjing-1$3.79/hr$7.58/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×2504 GBsa-brazil-1$3.83/hr$7.65/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×2504 GBsa-brazil-1$3.83/hr$7.65/hrLaunch ↗
Huawei Cloud GPU
0.0% 30dReferral link
×2504 GBeu-west-0$4.67/hr$9.33/hrLaunch ↗

LLMs that fit

ModelParams16-bit8-bit4-bit
Laguna-S 2.1
Poolside
118B 8B activeNeeds >8 GPUsNeeds >8 GPUsBarely fits on 7×
gpt-oss-120b
OpenAI
117B 5.1B activeNot releasedNot releasedBarely fits on 6×
Llama 3.1 70B
Meta
70BNeeds >8 GPUsBarely fits on 6×4× · 10 GB free
Qwen3.6 35B-A3B
Alibaba
35B 3B activeBarely fits on 7×Barely fits on 4×3× · 14.4 GB free
Qwen3 32B
Alibaba
32.8BBarely fits on 6×4× · 12.4 GB freeBarely fits on 2×
Qwen2.5 14B
Alibaba
14B3× · 12.6 GB free2× · 12.7 GB free1× · 4.6 GB free
Llama 3.1 8B
Meta
8B2× · 11.1 GB free1× · 4.6 GB free1× · 9.3 GB free
Mistral 7B
Mistral AI
7B2× · 13.8 GB free1× · 6 GB free1× · 10.1 GB free
Qwen3 4B
Alibaba
4B1× · 4.4 GB free1× · 9.6 GB free1× · 12.3 GB free

Estimates: model weights plus 20% for KV cache and runtime overhead, at short context lengths. Long contexts and large batches need more. Rows marked “tight” hold the weights but not that full margin. A ×N figure is the total VRAM across N of these GPUs and makes no claim about interconnect throughput.

Similar GPUs

Frequently asked questions

How much does the T4 cost per hour?

The cheapest T4 offering starts at $0.17/hr, and the market median is $1.41/hr.

Which cloud providers offer the T4?

We track T4 offerings from Alibaba Cloud GPU, Naver Cloud GPU, Huawei Cloud GPU, Tencent Cloud GPU.

How much VRAM does the T4 have?

The T4 has 16 GB of VRAM.

What LLMs can run on the T4?

With 16 GB of VRAM, the T4 can run 9 of our tracked models in 4-bit quantization, including Laguna-S 2.1, gpt-oss-120b, Qwen3.6 35B-A3B. 6 models fit in 16-bit precision.

What's the biggest LLM I can run on multiple T4s?

With 8× T4 (128 GB total), the largest tracked model that fits in 16-bit is Qwen2.5 14B (14B params), which needs 3× GPUs.

Where is the T4 cheapest?

The cheapest T4 offering in our catalog is Alibaba Cloud GPU at $0.32/hr per GPU-hour (×2).