Can NVIDIA GeForce RTX 5070 run FLUX.1 Dev?
12B parameter Image Gen model on 12GB GDDR7
VRAM Requirements
FLUX.1 Dev is a 12B parameter model. At full precision (FP16), it requires 32GB of VRAM. Your NVIDIA GeForce RTX 5070 has 12GB, so you'll need to quantize it to 4-bit (Q4) to fit.
Maximum quality, no quantization
Near-lossless, ~50% size reduction
Good quality, ~75% size reduction
Recommended system RAM: 32GB DDR5 (2x GPU VRAM minimum for model overflow)
What This Means in Practice
At 4-bit precision, FLUX.1 Dev fits in VRAM but generation will be slower and you may need to limit resolution or batch size. Image quality is generally preserved at Q4, but very complex compositions may show minor artifacts.
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. Use the FP8/NF4 quantized version for your VRAM.
NVIDIA GeForce RTX 5070 Specs
Other GPUs That Run FLUX.1 Dev
Other Image Gen Models on NVIDIA GeForce RTX 5070
About FLUX.1 Dev
State-of-the-art image generation. 16GB comfortable at FP8.