datacenter
Thuê Nvidia A16.
Ampere
64GB VRAM
250W
Price history
Daily median across providers.
Loading...
Where to rent it
All providers carrying this GPU.
No fresh prices yet.
AI models that fit
See all 26 →
Run these on this GPU.
- GPT-OSS 20B 1× · fp16
- InternLM 2.5 20B 1× · fp16
- LiquidAI: LFM2-24B-A2B 1× · fp16
Cloud instances
See all 9 →
Hyperscaler bundles.
Pre-configured on 3 clouds — from $0.94/hr total
($0.47/hr per GPU).
FAQ
Frequently asked.
What's a cloud instance bundle for the Nvidia A16?
A pre-configured VM that pairs the Nvidia A16 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 A16?
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 A16 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
$0.94/hr
Lowest $/hr per GPU
$0.47/hr
Providers
3
Instance shapes
9
| Provider | Instance | GPUs | vCPU | RAM | Disk | $/hr | $/hr per GPU | |
|---|---|---|---|---|---|---|---|---|
| vcg-a16-12c-128g-32vram | 2× | 12 | 128 GB | 700 GB | $0.94/hr | $0.47/hr | ||
| A16x2 | 2× | 12 | 128 GB | 700 GB | $1.12/hr | $0.56/hr | ||
| A16x2 | 2× | 12 | 128 GB | 700 GB | $1.12/hr | $0.56/hr | ||
| A16x2 | 2× | 12 | 128 GB | 700 GB | $1.12/hr | $0.56/hr | ||
| A16x2 | 2× | 12 | 128 GB | 700 GB | $1.12/hr | $0.56/hr | ||
| 2x A16_PCIE | 2× | 12 | 128 GB | 700 GB | $1.22/hr | $0.61/hr | ||
| 2x A16_PCIE | 2× | 12 | 128 GB | 700 GB | $1.22/hr | $0.61/hr | ||
| 2x A16_PCIE | 2× | 12 | 128 GB | 700 GB | $1.22/hr | $0.61/hr | ||
| 2x A16_PCIE | 2× | 12 | 128 GB | 700 GB | $1.22/hr | $0.61/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 A16?
A pre-configured VM that pairs the Nvidia A16 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 A16?
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 A16 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
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP8
FP8
INT4
INT4
INT4
INT4
INT4
INT4
Models that run on this GPU.
GPU-count + quantization recommendations covering fine-tuning, inference, and run-it-yourself scenarios on the Nvidia A16.
GPT-OSS 20B
by OpenAI
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
20B (4B active)
Context
128K tokens
InternLM 2.5 20B
by Shanghai AI Lab
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
20B
Context
1M tokens
LiquidAI: LFM2-24B-A2B
by Liquid
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
24B
Context
128K tokens
?
FP16
TheDrummer: Cydonia 24B V4.1
by Thedrummer
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
24B
Context
131K tokens
Mistral: Mistral Small 3.2 24B
by Mistral AI
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
24B
Context
128K tokens
Mistral: Mistral Small 3.1 24B
by Mistral AI
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
24B
Context
128K tokens
Mistral: Mistral Small 3
by Mistral AI
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
24B
Context
33K tokens
WizardLM-2 8x22B
by Microsoft
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
22B
Context
66K tokens
Baidu: ERNIE 4.5 21B A3B Thinking
by Baidu
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
21B
Context
131K tokens
Baidu: ERNIE 4.5 21B A3B
by Baidu
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
21B
Context
131K tokens
LFM2-24B-A2B
by Togethercomputer
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
24B
Context
33K tokens
nim/mistralai/mixtral-8x22b-instruct-v01
by Mistral AI
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
22B
Context
16K tokens
Mixtral 8X22b Instruct V0.1
by Mistral AI
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
22B
Context
66K tokens
Mistral-Small-3.2-24B-Instruct-2506
by Mistral AI
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
24B
Context
128K tokens
Mistral: Devstral Medium
by Mistral AI
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
24B
Context
131K tokens
Mistral: Devstral Small 1.1
by Mistral AI
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
24B
Context
131K tokens
Sarvam M
by Sarvamai
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
24B
Context
33K tokens
Reka Flash 3
by Rekaai
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
21B
Context
66K tokens
NVIDIA: Llama 3.3 Nemotron Super 49B V1.5
by Nvidia
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
49B
Context
131K tokens
nim/nvidia/llama-3.3-nemotron-super-49b-v1
by Nvidia
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
49B
Context
16K tokens
Llama 3.2 90B Vision
by Meta AI
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
90B
Context
128K tokens
Qwen: Qwen3 Next 80B A3B Thinking
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
80B
Context
262K tokens
Qwen: Qwen3 Next 80B A3B Instruct
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
80B
Context
262K tokens
Qwen3 Next 80B A3b Instruct Fp8
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
80B
nim/meta/llama-3.2-90b-vision-instruct
by Meta AI
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
90B
Context
16K tokens
Tencent: Hunyuan A13B Instruct
by Tencent
Required GPUs
1× Nvidia A16
Total VRAM
64 GB
Parameters
80B
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 A16?
A pre-configured VM that pairs the Nvidia A16 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 A16?
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 A16 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).