BFL
Image gen12B
Image gen

FLUX.1 Dev

FLUX · FLUX.1 Dev Non-Commercial License

State-of-the-art image generation. Significantly better prompt adherence and image quality than SDXL. 12B parameter transformer model (not diffusion UNet). FP16 requires 24GB VRAM, but Q4 quantization brings it to 8GB GPUs. Non-commercial license.

Parameters
12B
Architecture
Dense
Context
512 tokens
Released
2024-08-01
Engines
ComfyUI, Fooocus

Parameters

12B

VRAM

13 GB

Context

1K

Formats

3

GPUs

20

FLUX.1 Dev (12B) requires 13 GB VRAM at recommended quality (Q8_0). At efficient quality (Q4_K_M), it fits in 7.2 GB VRAM, making it compatible with the NVIDIA RTX 4060 Laptop (40-60W). On NVIDIA Grace Blackwell Ultra GB300, expect approximately 15 tok/s at FP16. For the best experience, Budget Home AI Server ($1,162) is recommended.

Source: OwnRig methodology

VRAM (Recommended)

13 GB

Quantization

Q8_0

File Size

12 GB

Max Context

1K tokens

Primary Use

Image gen

Memory

VRAM Requirements

QualityQuantizationVRAMFile Size
fullFP1623.8 GB23.8 GB
recommendedQ8_013 GB12 GB
efficientQ4_K_M7.2 GB6 GB

Compatible GPUs

20 devices
NVIDIA Grace Blackwell Ultra GB300FP1615 tok/sExcellent
NVIDIA GeForce RTX 4090FP16Excellent
AMD Radeon Pro W7900FP16Excellent
NVIDIA RTX PRO 6000 BlackwellFP16Excellent
NVIDIA RTX PRO 6000 Blackwell Max-QFP16Excellent
AMD Radeon RX 7900 XTXQ8_0Good
NVIDIA GeForce RTX 4060 Ti 16GBQ4_K_MAcceptable
NVIDIA RTX 4090 Laptop (150-175W)Q4_K_MAcceptable
AMD Radeon RX 9070Q4_K_MAcceptable
AMD Radeon RX 9060 XT 16GBQ4_K_MAcceptable
AMD Radeon RX 9060 XT 8GBQ4_K_MAcceptable
NVIDIA GeForce RTX 5060 Ti 16GBQ4_K_MAcceptable
NVIDIA GeForce RTX 4060 8GBQ4_K_MMarginal
NVIDIA RTX 4060 Laptop (40-60W)Q4_K_MMarginal
NVIDIA RTX 4070 Laptop (80-115W)Q4_K_MMarginal
AMD Radeon RX 7600Q4_K_M2 tok/sMarginal
NVIDIA GeForce RTX 5060 8GBQ4_K_MMarginal
Apple M3 Pro (18GB Unified)Q4_K_MNot viable
NVIDIA GeForce RTX 3080 10GBQ4_K_MNot viable
NVIDIA GeForce RTX 4070 Ti 12GBQ8_0Not viable

Showing 20 of 20 entries

Hardware

Recommended Builds

Complete PC builds that can run FLUX.1 Dev.

FAQ

Frequently Asked Questions

How much VRAM does FLUX.1 Dev need?
FLUX.1 Dev requires 13 GB VRAM at recommended quality (Q8_0). At lower quality settings, it can fit in as little as 7.2 GB.
What is the best GPU for FLUX.1 Dev?
The NVIDIA Grace Blackwell Ultra GB300 delivers the best performance for FLUX.1 Dev, achieving 15 tok/s at FP16 with an excellent rating.
Can I run FLUX.1 Dev on an RTX 4060 Ti?
Yes. On the NVIDIA GeForce RTX 4060 Ti 16GB, FLUX.1 Dev runs at – (Q4_K_M, acceptable).
What quantization should I use for FLUX.1 Dev?
For the best quality, use Q8_0 (13 GB VRAM). If your GPU has limited VRAM, Q4_K_M (7.2 GB) is the most efficient option with acceptable quality.

Related Guides

All models

Data confidence: estimated. Source

VRAM requirements are calculated from model parameters and may vary by inference engine, context length, and batch size. Performance estimates are based on community benchmarks and should be verified for your specific configuration.FLUX is a trademark of its respective owner. OwnRig is not affiliated with or endorsed by the model creator.