Image GenerationFLUXFLUX-1-dev

FLUX.1-dev

black-forest-labs/FLUX.1-dev

FLUX.1-dev, high quality text-to-image, 12B rectified flow.

Parameters

12B

Context

4K

Downloads

3.4M

Likes

9.8K

Architecture

flux

View on HuggingFace

GPU Requirements

VRAM / RAM / disk estimates by quantization and usage scenario

QuantizationMinimumRecommendedProduction
FP1616bit
47.6 GB
RAM 71.3 · Disk 73.9
50.9 GB
RAM 76.3 · Disk 99.9
55.5 GB
RAM 83.2 · Disk 138.9
FP88bit
25.4 GB
RAM 38.1 · Disk 56.4
27.7 GB
RAM 41.6 · Disk 82.4
31.3 GB
RAM 47.0 · Disk 121.4
INT88bit
25.4 GB
RAM 38.1 · Disk 56.4
27.7 GB
RAM 41.6 · Disk 82.4
31.3 GB
RAM 47.0 · Disk 121.4
AWQ4bit
14.8 GB
RAM 32.0 · Disk 48.0
16.6 GB
RAM 32.0 · Disk 74.0
19.7 GB
RAM 32.0 · Disk 113.0
GPTQ4bit
14.9 GB
RAM 32.0 · Disk 48.2
16.8 GB
RAM 32.0 · Disk 74.2
19.9 GB
RAM 32.0 · Disk 113.2
GGUF4bit
15.2 GB
RAM 32.0 · Disk 48.4
17.0 GB
RAM 32.0 · Disk 74.4
20.2 GB
RAM 32.0 · Disk 113.4

GPU Recommendations

Best ValueBEST

1× RTX 5090

32 GB VRAM

$244/mo

≈ 15.7 img/min

Effective production throughput ≈ 11 images/min

score 0.6361

Deploy on vast ↗
Cheapest

1× RTX 3090

24 GB VRAM

$78.7/mo

≈ 5.3 img/min

Effective production throughput ≈ 3.7 images/min

score 0.6795

Deploy on vast ↗
Performance

8× H100 SXM

640 GB VRAM

$9,357/mo

≈ 40.1 img/min

Effective production throughput ≈ 28.1 images/min

score 0.2416

Deploy on vast ↗
Min Complexity

1× RTX 4090

24 GB VRAM

$98.1/mo

≈ 12.4 img/min

Effective production throughput ≈ 8.7 images/min

score 0.6796

Deploy on vast ↗

💬 Community — real deployment experience

0 Articles · 0 Benchmarks

View Community →

GPUs that fit (single card)

RTX 3090

24 GB VRAM

$78.7

/mo · vast

RTX 4090

24 GB VRAM

$98.1

/mo · vast

RTX 4090D

24 GB VRAM

$117

/mo · vast

L4

24 GB VRAM

$148

/mo · vast

A10

24 GB VRAM

$176

/mo · vast

AmciHub

AI Model Deployment & Compute Intelligence — analyze AI model requirements, GPU performance, cloud pricing and deployment costs to find the right deployment solution.

© 2026 AmciHub. All rights reserved. Model → Requirement → GPU → Benchmark → Cloud → Cost → Recommendation