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
13 GB
Q8_0
12 GB
1K tokens
Image gen
VRAM Requirements
| Quality | Quantization | VRAM | File Size |
|---|---|---|---|
| full | FP16 | 23.8 GB | 23.8 GB |
| recommended | Q8_0 | 13 GB | 12 GB |
| efficient | Q4_K_M | 7.2 GB | 6 GB |
Compatible GPUs
20 devices| NVIDIA Grace Blackwell Ultra GB300 | FP16 | 15 tok/s | Excellent |
| NVIDIA GeForce RTX 4090 | FP16 | – | Excellent |
| AMD Radeon Pro W7900 | FP16 | – | Excellent |
| NVIDIA RTX PRO 6000 Blackwell | FP16 | – | Excellent |
| NVIDIA RTX PRO 6000 Blackwell Max-Q | FP16 | – | Excellent |
| AMD Radeon RX 7900 XTX | Q8_0 | – | Good |
| NVIDIA GeForce RTX 4060 Ti 16GB | Q4_K_M | – | Acceptable |
| NVIDIA RTX 4090 Laptop (150-175W) | Q4_K_M | – | Acceptable |
| AMD Radeon RX 9070 | Q4_K_M | – | Acceptable |
| AMD Radeon RX 9060 XT 16GB | Q4_K_M | – | Acceptable |
| AMD Radeon RX 9060 XT 8GB | Q4_K_M | – | Acceptable |
| NVIDIA GeForce RTX 5060 Ti 16GB | Q4_K_M | – | Acceptable |
| NVIDIA GeForce RTX 4060 8GB | Q4_K_M | – | Marginal |
| NVIDIA RTX 4060 Laptop (40-60W) | Q4_K_M | – | Marginal |
| NVIDIA RTX 4070 Laptop (80-115W) | Q4_K_M | – | Marginal |
| AMD Radeon RX 7600 | Q4_K_M | 2 tok/s | Marginal |
| NVIDIA GeForce RTX 5060 8GB | Q4_K_M | – | Marginal |
| Apple M3 Pro (18GB Unified) | Q4_K_M | – | Not viable |
| NVIDIA GeForce RTX 3080 10GB | Q4_K_M | – | Not viable |
| NVIDIA GeForce RTX 4070 Ti 12GB | Q8_0 | – | Not viable |
Showing 20 of 20 entries
Recommended Builds
Complete PC builds that can run FLUX.1 Dev.
AI Builder Workstation
Run every AI tool you need. Nothing leaves your machine
Runs 10 models
Extreme AI Workstation
Dual GPUs that run the biggest AI models at a smart price
Runs 8 models
High-End AI Workstation
Chat, generate images, and code with AI, all at once
Runs 8 models
High-End Home AI Server
Your household's private AI: chatbots, code tools, and more
Runs 12 models
Mid-Range AI Workstation
The sweet spot for AI: handles most models without overspending
Runs 8 models
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
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.