RTX A4500
The RTX A4500 is a cloud GPU with 20 GB of memory and 200 W TDP. It is currently available from 1 provider starting at $0.19/hr, with a market median of $0.38/hr across 3 offerings.
Best deal
Hardware specifications
- Architecture
- Ampere
- VRAM
- 20 GB
- Memory bandwidth
- 640 GB/s
- FP32
- 24 TFLOPS
- TDP
- 200 W
Same across all providers.
Market comparison
Offerings
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 6× |
gpt-oss-120b OpenAI | 117B 5.1B active | Not released | Not released | Barely fits on 5× |
Llama 3.1 70B Meta | 70B | Needs >8 GPUs | Barely fits on 5× | Barely fits on 3× |
Qwen3.6 35B-A3B Alibaba | 35B 3B active | 6× · 14% spare | Barely fits on 3× | 2× · 6.4 GB free |
Qwen3 32B Alibaba | 32.8B | Barely fits on 5× | 3× · 14% spare | 2× · 10 GB free |
Qwen2.5 14B Alibaba | 14B | Barely fits on 2× | Barely fits on 1× | 1× · 8.6 GB free |
Llama 3.1 8B Meta | 8B | 2× · 19.1 GB free | 1× · 8.6 GB free | 1× · 13.3 GB free |
Mistral 7B Mistral AI | 7B | Barely fits on 1× | 1× · 10 GB free | 1× · 14.1 GB free |
Qwen3 4B Alibaba | 4B | 1× · 8.4 GB free | 1× · 13.6 GB free | 1× · 16.3 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 A4500 cost per hour?
The cheapest RTX A4500 offering starts at $0.19/hr, and the market median is $0.38/hr.
Which cloud providers offer the RTX A4500?
We track RTX A4500 offerings from HardwareHQ.
How much VRAM does the RTX A4500 have?
The RTX A4500 has 20 GB of VRAM.
What LLMs can run on the RTX A4500?
With 20 GB of VRAM, the RTX A4500 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 A4500s?
With 8× RTX A4500 (160 GB total), the largest tracked model that fits in 16-bit is Qwen3.6 35B-A3B (35B params), which needs 6× GPUs.
Where is the RTX A4500 cheapest?
The cheapest RTX A4500 offering in our catalog is HardwareHQ at $0.19/hr per GPU-hour (×1).