Question 1

What AI models can run on H100 SXM?

Accepted Answer

The H100 SXM (80 GB VRAM) can run models including Llama-2-7b, Llama-2-7b-chat, NV-Llama2-13B-RLHF-RM, MediPhi-MedWiki, intent-aware-lfqa-qwen3-4b-baseline and more — 10 compatible models indexed so far. Compatible models are determined by whether the model's memory footprint fits within the GPU's 80 GB VRAM, potentially using quantization (Q8, Q6, or Q4) to reduce memory usage.

Question 2

What is the cheapest cloud option for H100 SXM?

Accepted Answer

The cheapest on-demand option for the H100 SXM is Vast.ai at $1.80/hr (1x-H100_SXM-32-65536). Spot/preemptible pricing is available at $0.00/hr. We track pricing across 83 providers to help you find the best deal.

Question 3

Is H100 SXM good for fine-tuning?

Accepted Answer

Yes, the H100 SXM is excellent for fine-tuning. With 80 GB of VRAM, it can handle full fine-tuning of models up to ~30B parameters and LoRA/QLoRA fine-tuning of much larger models. It's a top-tier choice for training workloads.

Question 4

How much VRAM does H100 SXM have?

Accepted Answer

The H100 SXM has 80 GB of VRAM (HBM3). It also offers 3350 GB/s memory bandwidth, 989.5 TFLOPS of FP16 compute, FP8 support for efficient inference.

Question 5

What quantization formats work on H100 SXM?

Accepted Answer

The H100 SXM supports the following quantization formats: FP16 (full precision), FP8, Q8 (8-bit), Q6 (6-bit), Q4 (4-bit). FP16 works for models up to ~40B parameters. FP8 halves memory vs FP16 with minimal quality loss. Q4 quantization lets models up to ~272B parameters (by VRAM estimate) fit on the H100 SXM.

Provider	On-demand	Spot	Actions
Vast.ai	$1.800/hr	$0.000/hr	Rent
RunPod	$2.890/hr	$2.890/hr	Rent Get $5–$500 free
Lambda	$3.290/hr	—	—
Nebius	$3.850/hr	$2.150/hr	—
Amazon Web Services	$6.880/hr	$2.478/hr	—
Microsoft Azure	$6.980/hr	$6.980/hr	—
Google Cloud	$9.797/hr	$0.971/hr	—

H100 SXM

Specifications

Cloud pricing

Compatible models

Compare this GPU

Frequently asked questions

VRAM	80 GB
Memory type	HBM3
Bandwidth	3350 GB/s
FP16 TFLOPS	989.5
FP8 support	Yes