A10
24 GB VRAM125 FP16 TFLOPS150 W TDP5 providers190 offerings28 regions
The A10 is a cloud GPU with 24 GB of memory and 150 W TDP. It is currently available from 5 providers starting at $0.19/hr, with a market median of $0.60/hr across 190 offerings.
$0.19/hr
Cheapest
on Alibaba Cloud GPU
$0.60/hr
Median
across 190 offerings
$11.97/hr
Most expensive
0.0%
90-day trend
Best deal
Hardware specifications
- Architecture
- Ampere
- VRAM
- 24 GB
- Memory bandwidth
- 600 GB/s
- FP16
- 125 TFLOPS
- FP32
- 31 TFLOPS
- TDP
- 150 W
Same across all providers.
Market comparison
All-time price history
Offerings
| Provider | Cloud | Count | vCPU | RAM | Region | Per GPU hr | SPOT | Total/hr | |
|---|---|---|---|---|---|---|---|---|---|
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | us-east-1 | $0.19/hr | — | $0.76/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | cn-shenzhen | $0.22/hr | — | $0.88/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | cn-heyuan | $0.22/hr | — | $0.88/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | cn-wulanchabu | $0.22/hr | — | $0.88/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | cn-shanghai | $0.22/hr | — | $0.88/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | cn-beijing | $0.22/hr | — | $0.88/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | cn-hangzhou | $0.22/hr | — | $0.88/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 256 GB | cn-beijing | $0.23/hr | — | $0.93/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 256 GB | cn-shenzhen | $0.23/hr | — | $0.93/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 256 GB | cn-heyuan | $0.23/hr | — | $0.93/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 256 GB | cn-shanghai | $0.23/hr | — | $0.93/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 256 GB | cn-wulanchabu | $0.23/hr | — | $0.93/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 256 GB | cn-hangzhou | $0.23/hr | — | $0.93/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 256 GB | us-east-1 | $0.24/hr | — | $0.95/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | ap-southeast-5 | $0.25/hr | — | $1.00/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 752 GB | cn-heyuan | $0.26/hr | — | $1.05/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 752 GB | cn-wulanchabu | $0.26/hr | — | $1.05/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 256 GB | ap-southeast-5 | $0.27/hr | — | $1.06/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 128 GB | ap-southeast-1 | $0.29/hr | — | $1.15/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 752 GB | ap-northeast-2 | $0.29/hr | — | $1.17/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 752 GB | cn-hangzhou | $0.29/hr | — | $1.17/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 752 GB | cn-guangzhou | $0.29/hr | — | $1.17/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 752 GB | cn-beijing | $0.29/hr | — | $1.17/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 752 GB | cn-shenzhen | $0.29/hr | — | $1.17/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 752 GB | cn-shanghai | $0.29/hr | — | $1.17/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 752 GB | cn-chengdu | $0.29/hr | — | $1.17/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 256 GB | ap-southeast-1 | $0.31/hr | — | $1.22/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 768 GB | cn-beijing | $0.31/hr | — | $1.22/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 768 GB | cn-hangzhou | $0.31/hr | — | $1.22/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 768 GB | cn-shanghai | $0.31/hr | — | $1.22/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 768 GB | us-east-1 | $0.38/hr | — | $1.52/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 752 GB | us-east-1 | $0.41/hr | — | $1.64/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 752 GB | cn-hongkong | $0.42/hr | — | $1.67/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 752 GB | ap-northeast-1 | $0.46/hr | — | $1.82/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 768 GB | ap-northeast-1 | $0.46/hr | — | $1.82/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 752 GB | ap-southeast-1 | $0.46/hr | — | $1.83/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 752 GB | ap-southeast-7 | $0.47/hr | — | $1.86/hr | Launch ↗ |
Alibaba Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 752 GB | eu-central-1 | $0.50/hr | — | $2.00/hr | Launch ↗ |
JD Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 218 GB | cn-east-2 | $1.50/hr | — | $5.98/hr | Launch ↗ |
JD Cloud GPU 0.0% 30dReferral link | — | ×4 | — | 218 GB | cn-north-1 | $1.50/hr | — | $5.98/hr | Launch ↗ |
LLMs that fit
| Model | Params | 16-bit | 8-bit | 4-bit |
|---|---|---|---|---|
Laguna-S 2.1 Poolside | 118B 8B active | Needs >8 GPUs | Barely fits on 8× | Barely fits on 5× |
gpt-oss-120b OpenAI | 117B 5.1B active | Not released | Not released | Barely fits on 4× |
Llama 3.1 70B Meta | 70B | Barely fits on 7× | Barely fits on 4× | 3× · 18 GB free |
Qwen3.6 35B-A3B Alibaba | 35B 3B active | 5× · 14% spare | 3× · 15.6 GB free | 2× · 14.4 GB free |
Qwen3 32B Alibaba | 32.8B | Barely fits on 4× | 3× · 20.4 GB free | 2× · 18 GB free |
Qwen2.5 14B Alibaba | 14B | 2× · 12.6 GB free | 1× · 4.7 GB free | 1× · 12.6 GB free |
Llama 3.1 8B Meta | 8B | Barely fits on 1× | 1× · 12.6 GB free | 1× · 17.3 GB free |
Mistral 7B Mistral AI | 7B | 1× · 5.8 GB free | 1× · 14 GB free | 1× · 18.1 GB free |
Qwen3 4B Alibaba | 4B | 1× · 12.4 GB free | 1× · 17.6 GB free | 1× · 20.3 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 A10 cost per hour?
The cheapest A10 offering starts at $0.19/hr, and the market median is $0.60/hr.
Which cloud providers offer the A10?
We track A10 offerings from Alibaba Cloud GPU, JD Cloud GPU.
How much VRAM does the A10 have?
The A10 has 24 GB of VRAM.
What LLMs can run on the A10?
With 24 GB of VRAM, the A10 can run 9 of our tracked models in 4-bit quantization, including Laguna-S 2.1, gpt-oss-120b, Qwen3.6 35B-A3B. 7 models fit in 16-bit precision.
What's the biggest LLM I can run on multiple A10s?
With 8× A10 (192 GB total), the largest tracked model that fits in 16-bit is Qwen3.6 35B-A3B (35B params), which needs 5× GPUs.
Where is the A10 cheapest?
The cheapest A10 offering in our catalog is Alibaba Cloud GPU at $0.19/hr per GPU-hour (×4).