FLUX.1 dev needs about 5.2 GB of memory at Q2_K (a 4.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 17 quants, from 0.1 GB (Q8_0) to 12.8 GB (Q8_0).
FLUX.1 dev – a 0.123 billion‑parameter image generation model in GGUF format
FLUX.1 dev is a 0.123 billion‑parameter model from the Flux family. It is available as a set of GGUF files quantized by second‑state. The model can be run with sd‑api‑server or LlamaEdge services.
Good at
- Image generation
- Stable diffusion compatibility
- Low‑memory quantization options
Limits
- No vision support beyond image generation
- Requires 8 k context for memory estimates
- License is other, not specified
Best for
- Local image generation on modest GPUs
- Testing new diffusion architectures
- Educational demos of Flux models
Who it’s for. Developers and researchers who want to experiment with Flux models locally. The model is suitable for those who can run GGUF files with llama.cpp or sd‑api‑server.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q2_K | 1.6 GB | 2.3 GB | Fits | Get file → | |
| Q3_K | 2.1 GB | 2.9 GB | Fits | Get file → | |
| Q4_0 | 2.8 GB | 3.6 GB | Fits | Get file → | |
| Q4_K | 2.8 GB | 3.6 GB | Fits | Get file → | |
| Q4_1 | 3.1 GB | 3.9 GB | Fits | Get file → | |
| Q5_0 | 3.4 GB | 4.3 GB | Fits | Get file → | |
| Q5_1 | 3.7 GB | 4.6 GB | Fits | Get file → | |
| Q2_K | 4.2 GB | 5.2 GB | Fits | Get file → | |
| Q8_0 | 5.2 GB | 6.3 GB | Fits | Get file → | |
| Q3_K | 5.4 GB | 6.5 GB | Fits | Get file → | |
| Q4_0 | 6.9 GB | 8.3 GB | Too big | Get file → | |
| Q4_K | 6.9 GB | 8.3 GB | Too big | Get file → | |
| Q4_1 | 7.7 GB | 9.1 GB | Too big | Get file → | |
| Q5_0 | 8.4 GB | 9.9 GB | Too big | Get file → | |
| Q5_1 | 9.1 GB | 10.7 GB | Too big | Get file → | |
| Q8_0 | 12.8 GB | 14.9 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 or Q4_K (file size 2.75 GB, memory 3.6 GB). For 16 GB VRAM, Q5_0 (file size 3.36 GB, memory 4.3 GB) or Q5_1 (file size 3.67 GB, memory 4.6 GB). Higher‑precision Q8_0 (file size 0.13 GB, memory 0.6 GB) offers best quality but needs more VRAM.
What GPU do you need for FLUX.1 dev?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q4_1 (3.1 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q2_K (4.2 GB file, about 5.2 GB in use).
- 8 GB VRAM: the best quant that fits is Q3_K (5.4 GB file, about 6.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_1 (9.1 GB file, about 10.7 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (12.8 GB file, about 14.9 GB in use).
Which FLUX.1 dev quant should you choose?
Q2_K (4.2 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
If memory is tight, the smallest file is Q8_0 at 0.1 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about FLUX.1 dev
How much VRAM does FLUX.1 dev need?
About 5.2 GB at Q2_K with an 8K context window. That is the 4.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run FLUX.1 dev on an 8 GB GPU?
Yes, with Q3_K: the 5.4 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of FLUX.1 dev GGUF?
It depends on the quant: Q8_0 is 0.1 GB, Q2_K is 1.6 GB, Q3_K is 2.1 GB, Q4_0 is 2.8 GB, Q4_K is 2.8 GB, Q4_1 is 3.1 GB and 11 more.
Where can I download FLUX.1 dev GGUF?
The files are on Hugging Face in the second-state/FLUX.1-dev-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does FLUX.1 dev use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run FLUX.1 dev on 8 GB VRAM?
Yes, using Q4_0 or Q4_K quantization, which require about 3.6 GB of VRAM at 8 k context.
What is the smallest quant file for this model?
The smallest is Q8_0 at 0.13 GB, requiring 0.6 GB of VRAM at 8 k context.
Is this model suitable for text‑to‑image generation?
Yes, FLUX.1 dev is designed for image generation and works with sd‑api‑server or LlamaEdge.