datacenter
Alquilar Nvidia A16.
Ampere
64GB VRAM
250W
Where to rent it
All providers carrying this GPU.
No fresh prices yet.
FAQ
Frequently asked.
How is the Nvidia A16 price calculated?
We pull live listings from each provider's public API, take the median hourly rate across active offers, and refresh every hour. The rate shown is the median, so a single low-ball spot offer can't distort the headline.
Why does the Nvidia A16 cost different amounts on different providers?
P2P marketplaces like Vast.ai aggregate offers from individual hosts who set their own rates — bidding pushes prices down. First-party clouds (Lambda, hyperscalers) charge a managed-service premium for support, SLAs, and integrated networking. Decentralized networks (io.net, Akash) settle in tokens, which adds volatility but often the lowest base rate.
Can I really train an LLM on a single Nvidia A16?
Depends on the model size. With 64GB of VRAM you can fine-tune 13B–34B models with LoRA, or run inference on 70B models at int4 quantization.
Spot vs on-demand on the Nvidia A16 — which should I rent?
On-demand keeps the same instance until you stop it; spot (or interruptible) is cheaper but the host can reclaim it when a higher-paying job lands. Use on-demand for training runs and anything stateful. Use spot for stateless inference, batch jobs, and experiments where a checkpoint every few minutes is enough to recover.
How is hourly billing measured for the Nvidia A16?
Most providers bill per-second once the instance is running, with a small minimum (often 60 seconds). A handful of first-party clouds round up to the minute. Either way, headline $/hr is the right comparison unit.
Does the region of the host affect the Nvidia A16 price?
Yes — US and EU regions usually carry a premium over LATAM, India, and parts of APAC, especially on first-party clouds. P2P marketplaces hide this behind one global price because supply moves wherever bids exist.
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
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
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.
How is the Nvidia A16 price calculated?
We pull live listings from each provider's public API, take the median hourly rate across active offers, and refresh every hour. The rate shown is the median, so a single low-ball spot offer can't distort the headline.
Why does the Nvidia A16 cost different amounts on different providers?
P2P marketplaces like Vast.ai aggregate offers from individual hosts who set their own rates — bidding pushes prices down. First-party clouds (Lambda, hyperscalers) charge a managed-service premium for support, SLAs, and integrated networking. Decentralized networks (io.net, Akash) settle in tokens, which adds volatility but often the lowest base rate.
Can I really train an LLM on a single Nvidia A16?
Depends on the model size. With 64GB of VRAM you can fine-tune 13B–34B models with LoRA, or run inference on 70B models at int4 quantization.
Spot vs on-demand on the Nvidia A16 — which should I rent?
On-demand keeps the same instance until you stop it; spot (or interruptible) is cheaper but the host can reclaim it when a higher-paying job lands. Use on-demand for training runs and anything stateful. Use spot for stateless inference, batch jobs, and experiments where a checkpoint every few minutes is enough to recover.
How is hourly billing measured for the Nvidia A16?
Most providers bill per-second once the instance is running, with a small minimum (often 60 seconds). A handful of first-party clouds round up to the minute. Either way, headline $/hr is the right comparison unit.
Does the region of the host affect the Nvidia A16 price?
Yes — US and EU regions usually carry a premium over LATAM, India, and parts of APAC, especially on first-party clouds. P2P marketplaces hide this behind one global price because supply moves wherever bids exist.