workstation
租用 Nvidia RTX A6000.
Ampere
48GB VRAM
300W
2020
From $0.32/hr
Per hour
$0.32
Per day
$7.64
Per week
$53.46
Per month
$229
Provider spread
12 providers ·
up to 73% cheaper at the low end
Cheapest · $0.32/hr on Nosana
Median $0.52/hr
Most expensive · $1.16/hr on AceCloud
Price history
Daily median across providers.
Loading...
Where to rent it
All providers carrying this GPU.
Buy vs rent
Should you rent or own?
Your usage
Rent on cloud
Per day
—
Per month
—
at $0.32/hr cheapest provider rate
Own on-prem
Electricity per day
—
300W TDP
Workloads
Suitable workloads.
AI models that fit
See all 13 →
Run these on this GPU.
- Qwen 2.5 72B 1× · int4
- Qwen2.5 72B Instruct 1× · int4
- Gemma 3 27B 1× · fp16
Cloud instances
See all 23 →
Hyperscaler bundles.
Pre-configured on 5 clouds — from $0.35/hr total
($0.35/hr per GPU).
FAQ
Frequently asked.
What's a cloud instance bundle for the Nvidia RTX A6000?
A pre-configured VM that pairs the Nvidia RTX A6000 with a fixed amount of vCPU, RAM, and SSD on a hyperscaler (AWS, Google Cloud, Azure, Oracle, Vultr, etc.). You pay one hourly rate for the whole bundle; the per-GPU rate on the table is just the bundle price divided by the GPU count.
Why is per-GPU pricing on instances different from raw GPU rental rates?
Hyperscaler bundles include managed networking, premium NVMe storage, an SLA, and 24/7 support. P2P marketplaces (Vast.ai, RunPod community, io.net) skip those line items, which is why their raw GPU rates are often 3–10× cheaper. The trade-off is reliability and integration: a hyperscaler instance plugs into your existing VPC, IAM, and observability stack out of the box.
Which hyperscaler is cheapest for the Nvidia RTX A6000?
Sort the table by the $/hr per GPU column — the lowest row is the cheapest hyperscaler today. Pricing shifts as providers re-price spot capacity and refresh quotas, so the leader can change week to week. Click Launch on a row to head to that provider's sign-up page (affiliate link, doesn't change the rate you pay).
Can I run my own image or container on these instances?
Yes. All listed hyperscalers expose standard compute APIs — bring your own AMI/image, mount custom volumes, install your own drivers, run any container runtime you like. The bundle just sets the hardware shape; the OS layer is yours to configure.
How do I get the cheapest rate on the Nvidia RTX A6000 overall?
If you can tolerate a P2P marketplace, the Overview tab's "Where to rent it" table usually has the lowest hourly rate by a wide margin. Use a hyperscaler bundle only when you need managed networking, SLAs, or are already inside that cloud's ecosystem (compliance, data-egress costs, IAM).
Cloud instance options
Pre-configured instances on hyperscalers.
Whole-instance bundles (GPU + vCPU + RAM + disk) on the major clouds. Per-GPU rate often drops as the count rises. View = spec page · Launch = sign up (affiliate).
Cheapest bundle
$0.35/hr
Lowest $/hr per GPU
$0.35/hr
Providers
5
Instance shapes
23
| Provider | Instance | GPUs | vCPU | RAM | Disk | $/hr | $/hr per GPU | |
|---|---|---|---|---|---|---|---|---|
| a6000_x1 | 1× | 6 | 48 GB | 100 GB | $0.35/hr | $0.35/hr | ||
| on-demand · A6000 | 1× | 28 | 58 GB | — | $0.50/hr | $0.50/hr | ||
| 1x A6000_PCIE | 1× | 28 | 58 GB | 100 GB | $0.54/hr | $0.54/hr | ||
| 1x A6000_PCIE_LOW_RAM | 1× | 6 | 24 GB | 256 GB | $0.54/hr | $0.54/hr | ||
| A6000 | 1× | 28 | 58 GB | 100 GB | $0.55/hr | $0.55/hr | ||
| 1x A6000_PCIE_HIGH_PERF | 1× | 12 | 64 GB | 256 GB | $0.56/hr | $0.56/hr | ||
| A6000_base | 1× | 6 | 24 GB | 256 GB | $0.63/hr | $0.63/hr | ||
| A6000_plus | 1× | 12 | 64 GB | 256 GB | $0.63/hr | $0.63/hr | ||
| N.RTXA6000.64 | 1× | 16 | 64 GB | — | $1.16/hr | $1.16/hr | ||
| N.RTXA6000.128 | 1× | 24 | 128 GB | — | $1.57/hr | $1.57/hr | ||
| 2x A6000_PCIE_LOW_RAM | 2× | 14 | 48 GB | 512 GB | $1.08/hr | $0.54/hr | ||
| 2x A6000_PCIE_HIGH_PERF | 2× | 30 | 128 GB | 512 GB | $1.13/hr | $0.56/hr | ||
| 2x A6000_PCIE | 2× | 14 | 96 GB | 512 GB | $1.13/hr | $0.56/hr | ||
| A6000_plusx2 | 2× | 30 | 128 GB | 512 GB | $1.25/hr | $0.63/hr | ||
| A6000_basex2 | 2× | 14 | 48 GB | 512 GB | $1.25/hr | $0.63/hr | ||
| A6000x2 | 2× | 14 | 96 GB | 512 GB | $1.25/hr | $0.63/hr | ||
| 4x A6000_PCIE_LOW_RAM | 4× | 30 | 96 GB | 1024 GB | $2.16/hr | $0.54/hr | ||
| 4x A6000_PCIE_HIGH_PERF | 4× | 54 | 256 GB | 1024 GB | $2.26/hr | $0.56/hr | ||
| 4x A6000_PCIE | 4× | 30 | 192 GB | 1024 GB | $2.26/hr | $0.56/hr | ||
| A6000x4 | 4× | 30 | 192 GB | 1024 GB | $2.51/hr | $0.63/hr | ||
| A6000_basex4 | 4× | 30 | 96 GB | 1024 GB | $2.51/hr | $0.63/hr | ||
| A6000_plusx4 | 4× | 54 | 256 GB | 1024 GB | $2.51/hr | $0.63/hr | ||
| 8x A6000_PCIE | 8× | 62 | 384 GB | 2560 GB | $4.51/hr | $0.56/hr |
Looking for the cheapest rate?
Hyperscaler bundles include managed networking + SLAs. Raw per-GPU rental on P2P marketplaces is typically 3–10× cheaper.
See raw rental rates on the Overview tab →
FAQ
Cloud instances — common questions.
What's a cloud instance bundle for the Nvidia RTX A6000?
A pre-configured VM that pairs the Nvidia RTX A6000 with a fixed amount of vCPU, RAM, and SSD on a hyperscaler (AWS, Google Cloud, Azure, Oracle, Vultr, etc.). You pay one hourly rate for the whole bundle; the per-GPU rate on the table is just the bundle price divided by the GPU count.
Why is per-GPU pricing on instances different from raw GPU rental rates?
Hyperscaler bundles include managed networking, premium NVMe storage, an SLA, and 24/7 support. P2P marketplaces (Vast.ai, RunPod community, io.net) skip those line items, which is why their raw GPU rates are often 3–10× cheaper. The trade-off is reliability and integration: a hyperscaler instance plugs into your existing VPC, IAM, and observability stack out of the box.
Which hyperscaler is cheapest for the Nvidia RTX A6000?
Sort the table by the $/hr per GPU column — the lowest row is the cheapest hyperscaler today. Pricing shifts as providers re-price spot capacity and refresh quotas, so the leader can change week to week. Click Launch on a row to head to that provider's sign-up page (affiliate link, doesn't change the rate you pay).
Can I run my own image or container on these instances?
Yes. All listed hyperscalers expose standard compute APIs — bring your own AMI/image, mount custom volumes, install your own drivers, run any container runtime you like. The bundle just sets the hardware shape; the OS layer is yours to configure.
How do I get the cheapest rate on the Nvidia RTX A6000 overall?
If you can tolerate a P2P marketplace, the Overview tab's "Where to rent it" table usually has the lowest hourly rate by a wide margin. Use a hyperscaler bundle only when you need managed networking, SLAs, or are already inside that cloud's ecosystem (compliance, data-egress costs, IAM).
AI models
INT4
INT4
FP16
FP16
FP16
INT4
INT8
INT4
INT4
FP16
INT4
INT8
INT4
Models that run on this GPU.
GPU-count + quantization recommendations covering fine-tuning, inference, and run-it-yourself scenarios on the Nvidia RTX A6000.
Qwen 2.5 72B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia RTX A6000
Total VRAM
48 GB
Parameters
73B
Context
128K tokens
Qwen2.5 72B Instruct
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia RTX A6000
Total VRAM
48 GB
Parameters
72B
Context
33K tokens
Gemma 3 27B
by Google DeepMind
Required GPUs
1× Nvidia RTX A6000
Total VRAM
48 GB
Parameters
27B (27B active)
Context
128K tokens
Llama 3.2 11B Vision
by Meta AI
Required GPUs
1× Nvidia RTX A6000
Total VRAM
48 GB
Parameters
11B
Context
128K tokens
Qwen 2.5 Coder 32B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia RTX A6000
Total VRAM
48 GB
Parameters
33B
Context
128K tokens
Qwen2 72B Instruct
by Togethercomputer
Required GPUs
1× Nvidia RTX A6000
Total VRAM
48 GB
Parameters
72B
Context
33K tokens
Qwen 2.5 72B
by Alibaba (Qwen Team)
Required GPUs
2× Nvidia RTX A6000
Total VRAM
96 GB
Parameters
73B
Context
128K tokens
Qwen2.5 72B Instruct Turbo
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia RTX A6000
Total VRAM
48 GB
Parameters
72B
Context
131K tokens
DeepSeek R1 Distill Llama 70B
by DeepSeek
Required GPUs
1× Nvidia RTX A6000
Total VRAM
48 GB
Parameters
70B
Context
128K tokens
DeepSeek R1 Distill Qwen 32B
by DeepSeek
Required GPUs
1× Nvidia RTX A6000
Total VRAM
48 GB
Parameters
33B
Context
128K tokens
Qwen2-VL (72B) Instruct
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia RTX A6000
Total VRAM
48 GB
Parameters
72B
Context
33K tokens
Llama 3.3 70B
by Meta AI
Required GPUs
2× Nvidia RTX A6000
Total VRAM
96 GB
Parameters
70B
Context
128K tokens
Qwen: Qwen2.5 VL 72B Instruct
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia RTX A6000
Total VRAM
48 GB
Parameters
72B
Context
131K tokens
Renting for inference?
Pair these models with the cheapest provider on the rental table.
See rental rates on the Overview tab →
FAQ
AI models on this GPU.
What's a cloud instance bundle for the Nvidia RTX A6000?
A pre-configured VM that pairs the Nvidia RTX A6000 with a fixed amount of vCPU, RAM, and SSD on a hyperscaler (AWS, Google Cloud, Azure, Oracle, Vultr, etc.). You pay one hourly rate for the whole bundle; the per-GPU rate on the table is just the bundle price divided by the GPU count.
Why is per-GPU pricing on instances different from raw GPU rental rates?
Hyperscaler bundles include managed networking, premium NVMe storage, an SLA, and 24/7 support. P2P marketplaces (Vast.ai, RunPod community, io.net) skip those line items, which is why their raw GPU rates are often 3–10× cheaper. The trade-off is reliability and integration: a hyperscaler instance plugs into your existing VPC, IAM, and observability stack out of the box.
Which hyperscaler is cheapest for the Nvidia RTX A6000?
Sort the table by the $/hr per GPU column — the lowest row is the cheapest hyperscaler today. Pricing shifts as providers re-price spot capacity and refresh quotas, so the leader can change week to week. Click Launch on a row to head to that provider's sign-up page (affiliate link, doesn't change the rate you pay).
Can I run my own image or container on these instances?
Yes. All listed hyperscalers expose standard compute APIs — bring your own AMI/image, mount custom volumes, install your own drivers, run any container runtime you like. The bundle just sets the hardware shape; the OS layer is yours to configure.
How do I get the cheapest rate on the Nvidia RTX A6000 overall?
If you can tolerate a P2P marketplace, the Overview tab's "Where to rent it" table usually has the lowest hourly rate by a wide margin. Use a hyperscaler bundle only when you need managed networking, SLAs, or are already inside that cloud's ecosystem (compliance, data-egress costs, IAM).