datacenter
租用 Nvidia H100 NVL.
Hopper
94GB VRAM
400W
Where to rent it
All providers carrying this GPU.
No fresh prices yet.
FAQ
Frequently asked.
How is the Nvidia H100 NVL 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 H100 NVL 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 H100 NVL?
Depends on the model size. With 94GB of VRAM you can fine-tune 70B models with QLoRA, or fully fine-tune 13B-class models.
Spot vs on-demand on the Nvidia H100 NVL — 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 H100 NVL?
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 H100 NVL 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
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
INT4
Models that run on this GPU.
GPU-count + quantization recommendations covering fine-tuning, inference, and run-it-yourself scenarios on the Nvidia H100 NVL.
Qwen 2.5 Coder 32B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
33B
Context
128K tokens
DeepSeek R1 Distill Qwen 32B
by DeepSeek
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
33B
Context
128K tokens
Qwen 2.5 32B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
33B
Context
128K tokens
Qwen 3 32B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
33B
Context
128K tokens
LLaVA 34B
by LLaVA Project
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
34B
Context
4K tokens
Code Llama 34B
by Meta AI
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
34B
Context
16K tokens
DeepSeek Coder 33B
by DeepSeek
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
33B
Context
16K tokens
Yi-34B
by 01.AI
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
34B
Context
32K tokens
Qwen: Qwen3.6 35B A3B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
35B
Context
262K tokens
Qwen: Qwen3.5-35B-A3B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
35B
Context
262K tokens
TheDrummer: Skyfall 36B V2
by Thedrummer
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
36B
Context
33K tokens
Holo3 35B A3b
by Hcompany
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
35B
Context
262K tokens
Deepseek Coder 33B Instruct
by DeepSeek
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
33B
Context
16K tokens
Qwen3.6 35B A3b Fp8
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
35B
Context
262K tokens
Llama 3.3 70B
by Meta AI
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
128K tokens
Qwen 2.5 72B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
73B
Context
128K tokens
DeepSeek R1 Distill Llama 70B
by DeepSeek
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
128K tokens
Llama 3.1 70B
by Meta AI
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
128K tokens
Code Llama 70B
by Meta AI
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
16K tokens
Hermes 3 70B
by Nous Research
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
128K tokens
Nous: Hermes 4 70B
by Nous Research
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
131K tokens
Qwen: Qwen2.5 VL 72B Instruct
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
72B
Context
131K tokens
Sao10K: Llama 3.1 70B Hanami x1
by Sao10k
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
16K tokens
Sao10K: Llama 3.3 Euryale 70B
by Sao10k
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
131K tokens
Magnum v4 72B
by Anthracite Org
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
72B
Context
33K tokens
Sao10K: Llama 3.1 Euryale 70B v2.2
by Sao10k
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
131K tokens
Sao10k: Llama 3 Euryale 70B v2.1
by Sao10k
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
8K tokens
Meta: Llama 3 70B Instruct
by Meta AI
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
8K tokens
Meta Llama 3.3 70B Instruct Turbo
by Meta AI
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
131K tokens
Meta Llama 3.1 70B Instruct Turbo
by Meta AI
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
131K tokens
nim/meta/llama-3.1-70b-instruct
by Meta AI
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
16K tokens
nim/nvidia/llama-3.1-nemotron-70b-instruct
by Nvidia
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
16K tokens
Cogito V1 Preview Llama 70B
by Deepcogito
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
131K tokens
Cogito V1 Preview Llama 70B Turbo
by Deepcogito
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
131K tokens
Qwen 2 (72B)
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
72B
Context
33K tokens
Qwen2.5 72B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
72B
Context
131K tokens
Llama 3.1 70B
by Meta AI
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
131K tokens
Meta Llama 3 70B Instruct Turbo
by Meta AI
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
8K tokens
nim/meta/llama-3.3-70b-instruct
by Meta AI
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
16K tokens
Llama 3.1 Nemotron 70B Instruct HF
by Nvidia
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
33K tokens
meta-llama/Llama-3.3-70B-Instruct
by Meta AI
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
131K tokens
Llama 3.3 70B Instruct FP8 Lora
by Meta AI
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
131K tokens
Qwen2.5 72B Instruct
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
72B
Context
33K tokens
Qwen2 72B Instruct
by Togethercomputer
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
72B
Context
33K tokens
Qwen2.5 72B Instruct Turbo
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
72B
Context
131K tokens
Qwen2-VL (72B) Instruct
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
72B
Context
33K tokens
Hermes-3-Llama-3.1-70B
by Nous Research
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
131K tokens
L3.1-70B-Euryale-v2.2
by Sao10k
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
131K tokens
Meta-Llama-3.1-70B-Instruct
by Meta AI
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
131K tokens
Xiaomi: MiMo-V2.5-Pro
by Xiaomi
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
65B
Context
1M tokens
Writer: Palmyra X5
by Writer
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
1M tokens
Morph: Morph V3 Large
by Morph
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
70B
Context
262K tokens
Mixtral 8x22B
by Mistral AI
Required GPUs
1× Nvidia H100 NVL
Total VRAM
94 GB
Parameters
141B (39B active)
Context
66K 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 H100 NVL 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 H100 NVL 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 H100 NVL?
Depends on the model size. With 94GB of VRAM you can fine-tune 70B models with QLoRA, or fully fine-tune 13B-class models.
Spot vs on-demand on the Nvidia H100 NVL — 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 H100 NVL?
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 H100 NVL 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.