canirunthismodel

Can I run FLUX.1-dev locally?

black-forest-labs/FLUX.1-dev
Text-to-image (diffusion)12B params54 GB download

FLUX.1-dev is a text-to-image (diffusion) model with about 12B parameters. The practical minimum to run it is roughly 31 GB of GPU or system memory, and a GPU with 31 GB VRAM runs it comfortably. Here's exactly what it needs and how to run it.

Check YOUR exact machine

FLUX.1-dev memory & VRAM requirements

How much memory FLUX.1-dev needs at each quantization level (weights plus ~20% runtime overhead). Lower-bit quantization dramatically reduces VRAM at a small quality cost.

PrecisionMemory neededNotes
Image pipeline31 GB

Will FLUX.1-dev run on your GPU?

Verdicts for common setups — from CPU-only laptops to an RTX 4090 and data-center GPUs. Click a GPU to see everything it can run.

Your setupVerdictNeedsBest way to run
No GPU (16 GB RAM)Too big31 GBUse CPU offload or a cloud GPU
RTX 4060 (8 GB)Too big31 GBUse CPU offload or a cloud GPU
RTX 3060 (12 GB)Too big31 GBUse CPU offload or a cloud GPU
RTX 4070 Super (12 GB)Too big31 GBUse CPU offload or a cloud GPU
RTX 4080 Super (16 GB)Too big31 GBUse CPU offload or a cloud GPU
RTX 4090 (24 GB)Workarounds31 GBUse CPU offload or a cloud GPU
RTX 3090 (24 GB)Workarounds31 GBUse CPU offload or a cloud GPU
Apple M-series (18 GB unified)Too big31 GBUse CPU offload or a cloud GPU
Apple M Max (64 GB unified)Runs31 GBRun on your GPU with Diffusers / ComfyUI
A100 (80 GB)Runs31 GBRun on your GPU with Diffusers / ComfyUI

How to run FLUX.1-dev locally

Recommended method: Run on your GPU with Diffusers / ComfyUI using ComfyUI or Diffusers.

Python (Diffusers)
from diffusers import DiffusionPipeline
import torch
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.float16)
pipe.enable_model_cpu_offload()  # saves VRAM
out = pipe("a photo of an astronaut")
Or use ComfyUI
# Easiest path for image/video diffusion models:
# 1. Install ComfyUI:  https://github.com/comfyanonymous/ComfyUI
# 2. Place the weights for black-forest-labs/FLUX.1-dev in ComfyUI/models/
# 3. Load a workflow template for this model

FLUX.1-dev — frequently asked questions

How much memory does FLUX.1-dev need?

FLUX.1-dev needs roughly 31 GB of GPU or system memory to run, including runtime overhead. The exact amount depends on precision, context length, and framework.

Can I run FLUX.1-dev on CPU without a GPU?

Not practically — FLUX.1-dev needs more memory than a typical CPU-only setup provides. Use a GPU with enough VRAM, GPU+CPU offload, or a cloud GPU.

What's the best way to run FLUX.1-dev locally?

The easiest path is usually ComfyUI or Diffusers. Run on your GPU with Diffusers / ComfyUI. This page's "How to run it" section has copy-paste commands.

What GPU do I need to run FLUX.1-dev?

A GPU with at least 31 GB of VRAM runs FLUX.1-dev comfortably at 4-bit quantization. On Apple Silicon, unified memory of that size works too.

Related models

Check this model on a specific GPU