NVIDIA RTX A4500

20 GB VRAM200 W TDP2 providers2 offerings1 regions

The NVIDIA RTX A4500 is an enterprise-class GPU built on the Ampere architecture, featuring 20 GB of memory with 640 GB/s of memory bandwidth and a 200 W TDP. It delivers 23.7 TFLOPS of FP32 performance. Currently available from 2 providers starting at $0.11/GPU/hour, with a market median of $0.18/GPU/hour across 2 configurations.

Cheapest

$0.110/hr

Vast.ai

Median

$0.180/hr

across 2 offerings

Most expensive

$0.250/hr

Runpod

90-day trend

-28.0%

median rate

Hardware specifications

Same across all providers

Memory

20 GB

What LLMs fit? ↓

TDP

200 W

Memory bandwidth

640 GB/s

Architecture

Ampere

FP32 performance

23.7 TFLOPS

Brand

NVIDIA

Series

RTX A

Market price history

Median price across all providers

Prices updated 3 hours ago

2 offerings from 2 providers

Sorted by price ascending. Compare configurations side-by-side.

Provider	Count	vCPU	RAM	Region	Per GPU hour	Total/hr	Action
RunpodPromoted Up to$500creditAffiliate promotion — we may earn a commission.	×1	—	—	--	$0.250	$0.25	Launch
Vast.aiReferral linkTrendingCheapest	×1	8	251 GB		$0.110 -91.3% 30d	$0.11	Launch
RunpodReferral linkTrending Up to$500credit	×1	—	—	--	$0.250	$0.25	Launch

LLMs that fit on the NVIDIA RTX A4500

Estimated VRAM for popular open-weight LLMs at 16-bit (FP16/BF16), 8-bit (FP8/INT8) and 4-bit (INT4/MXFP4) precision, against 20 GB per GPU.

Model	Parameters	16-bit	8-bit	4-bit
GLM-4.7 Flash Z.ai	31.2B	75 GB Too large	41 GB Too large	24 GB Tight on 1× · 0% spare
Qwen3.6 27B Alibaba	27.8B	67 GB Too large	37 GB Too large	21 GB Tight on 1× · 12% spare
Mistral Small 3.2 24B Mistral AI	24B	58 GB Too large	32 GB Too large	18 GB 1× · 1.6 GB free
gpt-oss-20b OpenAI	21B 3.6B active	— Not released	— Not released	17 GB 1× · 3.5 GB free
Gemma 3 12B Google	12.2B	29 GB Too large	16 GB 1× · 3.9 GB free	9.4 GB 1× · 11 GB free
Granite 4.1 8B IBM	8.8B	21 GB Tight on 1× · 13% spare	12 GB 1× · 8.4 GB free	6.8 GB 1× · 13 GB free
Qwen3 8B Alibaba	8.2B	20 GB Barely fits on 1×	11 GB 1× · 9.2 GB free	6.3 GB 1× · 14 GB free
Llama 3.1 8B Instruct Meta	8B	19 GB Barely fits on 1×	11 GB 1× · 9.4 GB free	6.2 GB 1× · 14 GB free
Mistral 7B Instruct v0.3 Mistral AI	7.2B	17 GB 1× · 2.6 GB free	9.6 GB 1× · 10 GB free	5.6 GB 1× · 14 GB free
Qwen3 4B Alibaba	4B	9.7 GB 1× · 10 GB free	5.3 GB 1× · 15 GB free	3.1 GB 1× · 17 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. How we estimate this · Start from a model instead

Want more from this page?

See incorrect data?

Frequently asked questions

How much does the RTX A4500 cost per hour?

The RTX A4500 starts at $0.11 per GPU-hour, with a median of $0.18 across 2 available configurations. Actual pricing depends on the provider, region, and whether you rent on-demand, spot or reserved.

Which cloud providers offer the RTX A4500?

2 providers currently list the RTX A4500: Vast.ai, Runpod. Compare their hourly pricing, regions and machine specs in the table above.

How much VRAM does the RTX A4500 have?

The RTX A4500 comes with 20 GB of VRAM, which determines the largest models and batch sizes it can hold in memory for training and inference.

Which LLMs can I run on the RTX A4500?

With 20 GB of VRAM, a single RTX A4500 can serve models such as Mistral Small 3.2 24B, gpt-oss-20b, Gemma 3 12B, Granite 4.1 8B. The table above lists the estimated VRAM for each model at 16-bit, 8-bit and 4-bit precision, including the multi-GPU configurations needed for larger models.

Where is the RTX A4500 cheapest?

The lowest on-demand price we currently track for the RTX A4500 is $0.11 per GPU-hour at Vast.ai. Because providers update pricing and availability frequently, check the live table above before you launch.