flux dev needs about 8.0 GB of memory at Q4_K_M (a 6.7 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 13 quants, from 0.2 GB (F16) to 12.7 GB (Q8_0).
Flux dev – a compact Flux model for low‑VRAM ComfyUI setups
Flux dev is a 0.123 billion‑parameter model built on the pig architecture. It is a repackaged version of FLUX.1‑dev, optimized for ComfyUI users with less than 24 GB VRAM. The model includes both text encoders and a VAE within a single safetensor file.
Good at
- Text‑to‑image generation
- Inpainting and outpainting workflows
- ComfyUI integration
Limits
- No vision support beyond text prompts
- Requires ComfyUI environment
- License type is other
Best for
- Artists needing lightweight text‑to‑image tools
- ComfyUI users with limited VRAM
- Rapid prototyping of diffusion workflows
Who it’s for. Developers and artists who use ComfyUI and need a smaller Flux checkpoint that runs on GPUs with under 24 GB of VRAM. The model is suitable for those who prefer a single safetensor file containing both the model and its encoders.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 0.2 GB | 0.7 GB | Fits | Get file → | |
| F16 | 0.2 GB | 0.8 GB | Fits | Get file → | |
| Q4_0 | 2.8 GB | 3.6 GB | Fits | Get file → | |
| Q2_K | 3.9 GB | 4.9 GB | Fits | Get file → | |
| Q3_K_M | 5.1 GB | 6.2 GB | Fits | Get file → | |
| Q4_0 | 6.7 GB | 8.0 GB | Too big | Get file → | |
| Q4_K_M | 6.7 GB | 8.0 GB | Too big | Get file → | |
| Q4_1 | 7.4 GB | 8.8 GB | Too big | Get file → | |
| Q5_0 | 8.2 GB | 9.7 GB | Too big | Get file → | |
| Q5_K_M | 8.2 GB | 9.7 GB | Too big | Get file → | |
| Q5_1 | 8.9 GB | 10.5 GB | Too big | Get file → | |
| Q6_K | 9.8 GB | 11.4 GB | Too big | Get file → | |
| Q8_0 | 12.7 GB | 14.7 GB | Too big | Get file → |
For 8 GB VRAM, the Q4_0 quant (file size 2.75 GB, estimated 3.6 GB memory at 8k context) is a good balance. If more memory is available, Q4_K_M (6.71 GB, 8 GB memory) or Q5_0 (8.19 GB, 9.7 GB memory) can be used. The F16 quant offers the smallest file size but requires more memory at 0.7–0.8 GB.
What GPU do you need for flux 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_0 (2.8 GB file, about 3.6 GB in use).
- 6 GB VRAM: the best quant that fits is Q2_K (3.9 GB file, about 4.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_K_M (6.7 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (9.8 GB file, about 11.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 14.7 GB in use).
Which flux dev quant should you choose?
Q4_K_M is the usual starting point for flux dev: it balances file size and quality well. Here it is a 6.7 GB file.
The Q8_0 file is 12.7 GB, about 1.9 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is F16 at 0.2 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about flux dev
How much VRAM does flux dev need?
About 8.0 GB at Q4_K_M with an 8K context window. That is the 6.7 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 dev on an 8 GB GPU?
Yes, with Q4_K_M: the 6.7 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of flux dev GGUF?
It depends on the quant: F16 is 0.2 GB, F16 is 0.2 GB, Q4_0 is 2.8 GB, Q2_K is 3.9 GB, Q3_K_M is 5.1 GB, Q4_0 is 6.7 GB and 7 more.
Where can I download flux dev GGUF?
The files are on Hugging Face in the gguf-org/flux-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 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 dev on 8 GB VRAM?
Yes, the Q4_0 quant uses about 3.6 GB of VRAM at 8k context, well within an 8 GB limit.
Does flux dev support image prompts?
The model is text‑only; image prompts are not supported in this version.
What is the license of flux dev?
The license is listed as other; check the repository for exact terms.