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
11-day price history
Offerings
| Provider | Cloud | Count | vCPU | RAM | Region | Per GPU hr | SPOT | Total/hr | |
|---|---|---|---|---|---|---|---|---|---|
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 372 GB | us-east-1 | $0.32/hr | — | $1.27/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 384 GB | us-east-1 | $0.32/hr | — | $1.27/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 372 GB | cn-hongkong | $0.33/hr | — | $1.30/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 372 GB | us-west-1 | $0.33/hr | — | $1.31/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 372 GB | ap-southeast-5 | $0.34/hr | — | $1.37/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 372 GB | ap-northeast-1 | $0.35/hr | — | $1.41/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 372 GB | cn-wulanchabu | $0.36/hr | — | $1.42/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 372 GB | cn-zhangjiakou | $0.36/hr | — | $1.42/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 372 GB | cn-chengdu | $0.36/hr | — | $1.42/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 384 GB | cn-zhangjiakou | $0.36/hr | — | $1.42/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 372 GB | eu-central-1 | $0.36/hr | — | $1.43/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 372 GB | ap-southeast-3 | $0.36/hr | — | $1.44/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 372 GB | ap-southeast-1 | $0.37/hr | — | $1.46/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 384 GB | ap-southeast-1 | $0.37/hr | — | $1.46/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 384 GB | cn-beijing | $0.40/hr | — | $1.58/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 372 GB | cn-beijing | $0.40/hr | — | $1.58/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 372 GB | cn-hangzhou | $0.40/hr | — | $1.58/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 384 GB | cn-heyuan | $0.40/hr | — | $1.58/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 384 GB | cn-shanghai | $0.40/hr | — | $1.58/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 384 GB | cn-shenzhen | $0.40/hr | — | $1.58/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 372 GB | cn-guangzhou | $0.40/hr | — | $1.58/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 384 GB | cn-hangzhou | $0.40/hr | — | $1.58/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 372 GB | cn-shenzhen | $0.40/hr | — | $1.58/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 372 GB | cn-shanghai | $0.40/hr | — | $1.58/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 372 GB | cn-qingdao | $0.40/hr | — | $1.58/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 372 GB | cn-heyuan | $0.40/hr | — | $1.58/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 372 GB | me-central-1 | $0.44/hr | — | $1.76/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | na-mexico-1 | $0.75/hr | — | $3.01/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | la-north-2 | $0.75/hr | — | $3.01/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | la-north-2 | $0.75/hr | — | $3.01/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | la-south-2 | $0.75/hr | — | $3.01/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | na-mexico-1 | $0.75/hr | — | $3.01/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | la-south-2 | $0.75/hr | — | $3.01/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | eu-west-101 | $0.80/hr | — | $3.18/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | eu-west-101 | $0.80/hr | — | $3.18/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | eu-west-0 | $0.87/hr | — | $3.46/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | me-east-1 | $0.92/hr | — | $3.69/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | me-east-1 | $0.92/hr | — | $3.69/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | my-kualalumpur-1 | $1.00/hr | — | $4.00/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | ap-southeast-3 | $1.00/hr | — | $4.00/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | ap-southeast-2 | $1.00/hr | — | $4.00/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | ap-southeast-2 | $1.00/hr | — | $4.00/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | ap-southeast-3 | $1.00/hr | — | $4.00/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | my-kualalumpur-1 | $1.00/hr | — | $4.00/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | cn-southwest-2 | $1.04/hr | — | $4.14/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | cn-southwest-2 | $1.04/hr | — | $4.14/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | cn-south-1 | $1.05/hr | — | $4.18/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | cn-north-4 | $1.05/hr | — | $4.18/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | cn-east-2 | $1.05/hr | — | $4.18/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | cn-east-2 | $1.05/hr | — | $4.18/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | cn-east-3 | $1.05/hr | — | $4.18/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | cn-east-3 | $1.05/hr | — | $4.18/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | cn-north-4 | $1.05/hr | — | $4.18/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | cn-south-1 | $1.05/hr | — | $4.18/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | af-south-1 | $1.05/hr | — | $4.21/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | af-south-1 | $1.05/hr | — | $4.21/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | sa-brazil-1 | $1.15/hr | — | $4.60/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | sa-brazil-1 | $1.15/hr | — | $4.60/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | ap-southeast-1 | $1.16/hr | — | $4.63/hr | Launch ↗ |
Huawei Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | ap-southeast-1 | $1.16/hr | — | $4.63/hr | Launch ↗ |
Tencent Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 384 GB | ap-beijing-6 | $1.17/hr | — | $4.69/hr | Launch ↗ |
Tencent Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 384 GB | ap-beijing-8 | $1.17/hr | — | $4.69/hr | Launch ↗ |
Tencent Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 384 GB | ap-beijing-7 | $1.30/hr | — | $5.21/hr | Launch ↗ |
Tencent Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 384 GB | ap-nanjing-1 | $1.30/hr | — | $5.21/hr | Launch ↗ |
Tencent Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 384 GB | ap-shanghai-5 | $1.30/hr | — | $5.21/hr | Launch ↗ |
Tencent Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 320 GB | na-ashburn-2 | $1.32/hr | — | $5.26/hr | Launch ↗ |
Tencent Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 320 GB | ap-seoul-2 | $1.47/hr | — | $5.88/hr | Launch ↗ |
Tencent Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 384 GB | na-siliconvalley-2 | $1.69/hr | — | $6.77/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 384 GB | cn-chengdu | $2.30/hr | — | $9.19/hr | Launch ↗ |
LLMs that fit
| Model | Params | 16-bit | 8-bit | 4-bit |
|---|---|---|---|---|
Laguna-S 2.1 Poolside | 118B 8B active | Needs >8 GPUs | Needs >8 GPUs | Barely fits on 7× |
gpt-oss-120b OpenAI | 117B 5.1B active | Not released | Not released | Barely fits on 6× |
Llama 3.1 70B Meta | 70B | Needs >8 GPUs | Barely fits on 6× | 4× · 10 GB free |
Qwen3.6 35B-A3B Alibaba | 35B 3B active | Barely fits on 7× | Barely fits on 4× | 3× · 14.4 GB free |
Qwen3 32B Alibaba | 32.8B | Barely fits on 6× | 4× · 12.4 GB free | Barely fits on 2× |
Qwen2.5 14B Alibaba | 14B | 3× · 12.6 GB free | 2× · 12.7 GB free | 1× · 4.6 GB free |
Llama 3.1 8B Meta | 8B | 2× · 11.1 GB free | 1× · 4.6 GB free | 1× · 9.3 GB free |
Mistral 7B Mistral AI | 7B | 2× · 13.8 GB free | 1× · 6 GB free | 1× · 10.1 GB free |
Qwen3 4B Alibaba | 4B | 1× · 4.4 GB free | 1× · 9.6 GB free | 1× · 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
See more GPUs like this in
Current generation
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, 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 (×4).