PlanetGPU
Search/A6000

A6000

48GB 300W 3 providers 80 offers

The Ampere RTX A6000 (48 GB) — a proven workstation GPU for large-memory inference and training.

Cheapest
$0.213/hr
Verda
Median
$2.180/hr
across 80 offers
P90
$4.360/hr
90th percentile
Prices updated 1 hour ago3 providers trackedHow we collect prices
Memory
48 GB
TDP
300 W
Bandwidth
768 GB/s
FP16
155 TFLOPS
Brand
NVIDIA
Series
NVIDIA
Year
2020
Arch
Ampere

Price by provider

cheapest rate · $/GPU/hr · lower is better
Verda
0 regions
$0.213/hr
RunPod
0 regions
$0.490/hr
Lambda
0 regions
$1.090/hr

3 providers

ProviderPrice RangeMedianTypeCPU / RAMAction
VE
Verda
Best price
$0.213$4.880
$1.037 Spot
10-80
60-480GB
Browse
RU
RunPod
$0.490$0.490
$0.490 Spot
12-12
62-62GB
Browse
LA
Lambda
$1.090$4.360
$2.180Mixed
14-56
107-430GB
Browse
Best Deal Right Now
VE
Verda
$0.213/hr
per GPU / hour
Configurationx1 · RTX A6000
System RAM60-480GB
Region—
Launch on Verda

Estimated Running Cost

At cheapest rate · per GPU

1 hour$0.21
24 hours$5.12
1 week$35.87
1 month$3740.52

Available At

VE
Verda
$0.213/hr
RU
RunPod
$0.490/hr
LA
Lambda
$1.090/hr

Compare

See how A6000 stacks up against other GPUs.

A6000 vs H100

Explore NVIDIA RTX A6000

Related comparisons, provider pages, raw specs, and model-fit tools.

NVIDIA RTX A6000 vs NVIDIA H100Compare live rental prices, VRAM, FP16 throughput, and provider availability.NVIDIA RTX A6000 vs NVIDIA H200Compare live rental prices, VRAM, FP16 throughput, and provider availability.NVIDIA RTX A6000 vs NVIDIA A100Compare live rental prices, VRAM, FP16 throughput, and provider availability.NVIDIA RTX A6000 on VerdaSee SKUs, regions, spot status, and current prices from $0.213/hr.NVIDIA RTX A6000 on RunPodSee SKUs, regions, spot status, and current prices from $0.490/hr.NVIDIA RTX A6000 on LambdaSee SKUs, regions, spot status, and current prices from $1.090/hr.NVIDIA RTX A6000 full specificationsOpen the raw GPU Ark spec detail page for clocks, memory, cores, and API fields.Find models that fit this class of GPUMatch LLM size and precision to GPUs with enough VRAM.