Can NVIDIA H100 80GB run FLUX.1 Dev?
12B parameter Image Gen model on 80GB HBM3
VRAM Requirements
FLUX.1 Dev is a 12B parameter model. At full precision (FP16), it requires 32GB of VRAM. Your NVIDIA H100 80GB has 80GB — enough to run it without any quantization.
Maximum quality, no quantization
Near-lossless, ~50% size reduction
Good quality, ~75% size reduction
Recommended system RAM: 160GB DDR5 (2x GPU VRAM minimum for model overflow)
What This Means in Practice
NVIDIA H100 80GB runs FLUX.1 Dev at full precision with room to spare. You can generate high-resolution images, use complex prompts, and batch multiple generations. Expect fast generation times at 1024x1024 and above.
How to Set It Up
Step 1: Install ComfyUI
git clone https://github.com/comfyanonymous/ComfyUI.git && cd ComfyUI && pip install -r requirements.txtComfyUI is the recommended UI for Stable Diffusion and FLUX models.
Step 2: Download the model
Download FLUX.1 Dev weights from HuggingFace and place them in ComfyUI/models/. The model is approximately 32GB at full precision.
Step 3: Launch and generate
python main.pyOpen http://localhost:8188 in your browser. You can use the full precision weights.
NVIDIA H100 80GB Specs
Other GPUs That Run FLUX.1 Dev
Other Image Gen Models on NVIDIA H100 80GB
About FLUX.1 Dev
State-of-the-art image generation. 16GB comfortable at FP8.