FLUX.2 [dev] VRAM Requirements
Developed by Black Forest Labs
Determine the local VRAM and system RAM requirements to run the FLUX.2 [dev] image generation model. Calculate components footprint, check VRAM margins, and optimize configurations for local generation speed.
Hardware Configuration
Adjust settings to check compatibility with your system in real time.
Available: 14.50 GB
Available: 29.00 GB
This configuration exceeds your system's usable memory capacity. Attempting to run it will cause crashes or freeze your machine.
Requires 63.65 GB total memory (weights: 57.69 GB, overhead: 5.96 GB).
FLUX.2 [dev] Precision Variants
FLUX.2 [dev] Component VRAM Breakdown
How to Setup and Run FLUX.2 [dev] Locally
Download Weights from Hugging Face
Open-source image model weights are hosted on Hugging Face. You will need to download the model files (safetensors or GGUF variants) and place them in your UI's model folder.
Setup inside ComfyUI or WebUI
Most image models require a generation framework:
- ComfyUI (Recommended): Put the UNet/Transformer weight files inside `ComfyUI/models/checkpoints/` or `ComfyUI/models/unet/` and the VAE inside `ComfyUI/models/vae/`.
- Stable Diffusion WebUI (Forge/re-forge): Put checkpoint files inside `webui/models/Stable-diffusion/`.
Model Specs
- DeveloperBlack Forest Labs
- AvailabilityLocal-Only
- Official SiteVisit site
Key Strengths
Commercial API Pricing
This model is self-hosted only with no commercial API endpoints.
Model Release Alerts
Get notified when new models drop that run on your hardware. Zero spam.