NVIDIA H100 NVL

94 GB VRAM2 providers2 offerings2 regions

The NVIDIA H100 NVL is an enterprise-class GPU built on the Hopper architecture, featuring 94 GB of memory. Currently available from 2 providers starting at $2.67/GPU/hour, with a market median of $2.93/GPU/hour across 2 configurations.

Cheapest

$2.670/hr

Vast.ai

Median

$2.930/hr

across 2 offerings

Most expensive

$3.190/hr

Runpod

90-day trend

+21.1%

median rate

Hardware specifications

Same across all providers

Memory

94 GB

HBM3

What LLMs fit? ↓

Architecture

Hopper

Brand

NVIDIA

Series

H100

Market price history

Median price across all providers

Prices updated 46 minutes ago

4 offerings from 2 providers

Sorted by price ascending. Compare configurations side-by-side.

Provider	Count	vCPU	RAM	Region	Per GPU hour	Total/hr	Action
RunpodPromoted Up to$500creditAffiliate promotion — we may earn a commission.	×1	16	180 GB		$3.190	$3.19	Launch
Vast.aiReferral linkTrendingCheapest	×1	40	314 GB		$2.670 +0.6% 30d	$2.67	Launch
RunpodReferral linkTrending Up to$500credit	×1	16	180 GB		$3.190	$3.19	Launch
Sesterce CloudReferral link	×2	40	256 GB	--	$3.476	From$6.95
OblivusReferral link	×8	252	1.41 TB		$3.640	$29.12

LLMs that fit on the NVIDIA H100 NVL

Estimated VRAM for popular open-weight LLMs at 16-bit (FP16/BF16), 8-bit (FP8/INT8) and 4-bit (INT4/MXFP4) precision, against 94 GB per GPU. Showing the 12 largest that fit.

Model	Parameters	16-bit	8-bit	4-bit
Laguna-S 2.1 Poolside	118B 8B active	282 GB Too large	155 GB Too large	90 GB 1× · 3.7 GB free
gpt-oss-120b OpenAI	117B 5.1B active	— Not released	— Not released	78 GB 1× · 16 GB free
Qwen3.6 35B-A3B Alibaba	35B 3B active	86 GB 1× · 7.7 GB free	47 GB 1× · 47 GB free	28 GB 1× · 66 GB free
Qwen3 32B Alibaba	32.8B	79 GB 1× · 15 GB free	43 GB 1× · 51 GB free	25 GB 1× · 69 GB free
Gemma 4 31B Google	31.3B	75 GB 1× · 19 GB free	41 GB 1× · 53 GB free	24 GB 1× · 70 GB free
GLM-4.7 Flash Z.ai	31.2B	75 GB 1× · 19 GB free	41 GB 1× · 53 GB free	24 GB 1× · 70 GB free
Qwen3.6 27B Alibaba	27.8B	67 GB 1× · 27 GB free	37 GB 1× · 57 GB free	21 GB 1× · 73 GB free
Mistral Small 3.2 24B Mistral AI	24B	58 GB 1× · 36 GB free	32 GB 1× · 62 GB free	18 GB 1× · 76 GB free
gpt-oss-20b OpenAI	21B 3.6B active	— Not released	— Not released	17 GB 1× · 77 GB free
Gemma 3 12B Google	12.2B	29 GB 1× · 65 GB free	16 GB 1× · 78 GB free	9.4 GB 1× · 85 GB free
Granite 4.1 8B IBM	8.8B	21 GB 1× · 73 GB free	12 GB 1× · 82 GB free	6.8 GB 1× · 87 GB free
Qwen3 8B Alibaba	8.2B	20 GB 1× · 74 GB free	11 GB 1× · 83 GB free	6.3 GB 1× · 88 GB free

Estimates: model weights plus 20% for KV cache and runtime overhead, at short context lengths. Long contexts and large batches need more. Rows marked “tight” hold the weights but not that full margin. A ×N figure is the total VRAM across N of these GPUs and makes no claim about interconnect throughput. How we estimate this · Start from a model instead

See more GPUs like this in

Highest performance

Want more from this page?

See incorrect data?

Frequently asked questions

How much does the H100 NVL cost per hour?

The H100 NVL starts at $2.67 per GPU-hour, with a median of $2.93 across 2 available configurations. Actual pricing depends on the provider, region, and whether you rent on-demand, spot or reserved.

Which cloud providers offer the H100 NVL?

4 providers currently list the H100 NVL: Sesterce Cloud, Oblivus, Vast.ai, Runpod. Compare their hourly pricing, regions and machine specs in the table above.

How much VRAM does the H100 NVL have?

The H100 NVL comes with 94 GB of VRAM, which determines the largest models and batch sizes it can hold in memory for training and inference.

Which LLMs can I run on the H100 NVL?

With 94 GB of VRAM, a single H100 NVL can serve models such as Laguna-S 2.1, gpt-oss-120b, Qwen3.6 35B-A3B, Qwen3 32B. The table above lists the estimated VRAM for each model at 16-bit, 8-bit and 4-bit precision, including the multi-GPU configurations needed for larger models.

Where is the H100 NVL cheapest?

The lowest on-demand price we currently track for the H100 NVL is $2.67 per GPU-hour at Vast.ai. Because providers update pricing and availability frequently, check the live table above before you launch.