RunLocalAI
nvidia
GPU
188GB VRAM
workstation

NVIDIA H100 NVL

Dual-card H100 with 188GB combined memory. Built for LLM serving.

Released 2023

Overview

Dual-card H100 with 188GB combined memory. Built for LLM serving.

Specs

VRAM188 GB
Power draw800 W
Released2023
MSRP$60000
Backends
CUDA

Models that fit

Open-weight models small enough to run on NVIDIA H100 NVL with usable context.

Llama 3.1 8B Instruct
8B · llama
Llama 4 Scout
109B · llama
Qwen 3 30B-A3B
30B · qwen
Qwen 2.5 Coder 32B Instruct
32B · qwen
Llama 3.3 70B Instruct
70B · llama
Qwen 3 32B
32B · qwen
Gemma 4 31B Dense
31B · gemma
Qwen 3 8B
8B · qwen

Frequently asked

What models can NVIDIA H100 NVL run?

With 188GB VRAM, the NVIDIA H100 NVL runs 70B models in 4-bit quantization, plus everything smaller. See the model list below for tested combinations.

Does NVIDIA H100 NVL support CUDA?

Yes — NVIDIA H100 NVL is an NVIDIA card with full CUDA support, the most mature local-AI backend. llama.cpp, Ollama, vLLM, and ExLlamaV2 all run natively.

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify hardware specifications.