RTX A4000
The RTX A4000 is a cloud GPU with 16 GB of memory and 140 W TDP. It is currently available from 4 providers starting at $0.06/hr, with a market median of $0.13/hr across 33 offerings.
Best deal
Hardware specifications
- Architecture
- Ampere
- VRAM
- 16 GB
- Memory bandwidth
- 448 GB/s
- FP32
- 19 TFLOPS
- TDP
- 140 W
Same across all providers.
Market comparison
10-day price history
Offerings
| Provider | Cloud | Count | vCPU | RAM | Region | Per GPU hr | SPOT | Total/hr | |
|---|---|---|---|---|---|---|---|---|---|
GPU Finder 0.0% 30d | — | ×1 | — | — | Japan, JP | $0.06/hr | — | $0.06/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Japan, JP | $0.06/hr | — | $0.06/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Kazakhstan, KZ | $0.07/hr | $0.05/hr | $0.07/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Kentucky, US | $0.08/hr | $0.04/hr | $0.08/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Italy, IT | $0.08/hr | $0.05/hr | $0.08/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Michigan, US | $0.08/hr | $0.05/hr | $0.08/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Germany, DE | $0.08/hr | $0.05/hr | $0.08/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Quebec, CA | $0.08/hr | $0.05/hr | $0.08/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Ohio, US | $0.09/hr | — | $0.09/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Australia, AU | $0.09/hr | $0.05/hr | $0.09/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Poland, PL, The Netherlands, NL | $0.09/hr | $0.08/hr | $0.09/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Alberta, CA | $0.10/hr | $0.09/hr | $0.10/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Estonia, EE | $0.10/hr | — | $0.10/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Romania, RO | $0.11/hr | — | $0.11/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Delaware, US | $0.11/hr | — | $0.11/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Norway, NO | $0.12/hr | $0.09/hr | $0.12/hr | Launch ↗ |
AutoDL 0.0% 30dReferral link | — | ×1 | — | — | CN | $0.13/hr | — | $0.13/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | France, FR | $0.13/hr | $0.11/hr | $0.13/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | oslo-norway-1 | $0.15/hr | — | $0.15/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | NO | $0.15/hr | — | $0.15/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | NORWAY-1 | $0.15/hr | — | $0.15/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | oslo-norway-1 | $0.15/hr | — | $0.15/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Iceland, IS | $0.16/hr | $0.15/hr | $0.16/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Global | $0.17/hr | — | $0.17/hr | Launch ↗ |
HardwareHQ 0.0% 30dReferral link | — | ×1 | — | — | — | $0.17/hr | — | $0.17/hr | Launch ↗ |
RunPodPromoted 0.0% 30dReferral link | Community | ×1 | — | — | — | $0.17/hr | — | $0.17/hr | Launch ↗ |
RunPodPromoted 0.0% 30dReferral link | Secure | ×1 | — | — | — | $0.25/hr | — | $0.25/hr | Launch ↗ |
HardwareHQ 0.0% 30dReferral link | — | ×2 | — | — | — | $0.17/hr | — | $0.34/hr | Launch ↗ |
HardwareHQ 0.0% 30dReferral link | — | ×4 | — | — | — | $0.17/hr | — | $0.68/hr | Launch ↗ |
HardwareHQ 0.0% 30dReferral link | — | ×1 | — | 45 GB | — | $0.76/hr | — | $0.76/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | newyork-usa-1 | $0.80/hr | — | $0.80/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | British Columbia, CA | $0.96/hr | $0.40/hr | $0.96/hr | Launch ↗ |
HardwareHQ 0.0% 30dReferral link | — | ×8 | — | — | — | $0.17/hr | — | $1.36/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
Frequently asked questions
How much does the RTX A4000 cost per hour?
The cheapest RTX A4000 offering starts at $0.06/hr, and the market median is $0.13/hr.
Which cloud providers offer the RTX A4000?
We track RTX A4000 offerings from GPU Finder, AutoDL, HardwareHQ, RunPod.
How much VRAM does the RTX A4000 have?
The RTX A4000 has 16 GB of VRAM.
What LLMs can run on the RTX A4000?
With 16 GB of VRAM, the RTX A4000 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 RTX A4000s?
With 8× RTX A4000 (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 RTX A4000 cheapest?
The cheapest RTX A4000 offering in our catalog is GPU Finder at $0.06/hr per GPU-hour (×1).