flux2 dev needs about 22.9 GB of memory at Q4_K_M (a 20.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 0.2 GB (F16) to 35.5 GB (Q8_0).
Flux2 dev: 17.8B parameter diffusion model in GGUF format
Flux2 dev is a 17.8 billion parameter diffusion model based on the Flux architecture. It is available in multiple GGUF quantizations from F16 to Q8_0. The model is compatible with ComfyUI via the pig VAE and flux2 diffusion model paths.
Good at
- Diffusion image generation
- Custom prompt handling
- ComfyUI integration
Limits
- No vision support in this GGUF release
- Large memory requirement for higher quants
- License type is other
Best for
- Creating high‑quality images from text prompts
- Fine‑tuning diffusion models
- Running on local GPUs with sufficient VRAM
Who it’s for. Developers and researchers who need a flexible diffusion model in GGUF format. The model works best with ComfyUI setups that support the pig VAE and flux2 diffusion model paths.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q2_K | 7.7 GB | 9.2 GB | Too big | Get file → | |
| IQ4_XS | 11.1 GB | 13.0 GB | Too big | Get file → | |
| Q4_0 | 11.6 GB | 13.5 GB | Too big | Get file → | |
| Q2_K | 12.4 GB | 14.4 GB | Too big | Get file → | |
| Q3_K_S | 15.6 GB | 18.0 GB | Too big | Get file → | |
| Q3_K_M | 15.9 GB | 18.3 GB | Too big | Get file → | |
| Q3_K_L | 16.1 GB | 18.5 GB | Too big | Get file → | |
| IQ4_XS | 18.8 GB | 21.6 GB | Too big | Get file → | |
| IQ4_NL | 19.8 GB | 22.7 GB | Too big | Get file → | |
| Q4_0 | 19.8 GB | 22.7 GB | Too big | Get file → | |
| Q4_K_S | 19.8 GB | 22.7 GB | Too big | Get file → | |
| Q8_0 | 20.0 GB | 22.9 GB | Too big | Get file → | |
| Q4_K_M | 20.0 GB | 22.9 GB | Too big | Get file → | |
| Q4_1 | 21.8 GB | 24.9 GB | Too big | Get file → | |
| Q5_0 | 23.7 GB | 27.1 GB | Too big | Get file → | |
| Q5_K_S | 23.7 GB | 27.1 GB | Too big | Get file → | |
| Q5_K_M | 24.0 GB | 27.3 GB | Too big | Get file → | |
| Q5_1 | 25.7 GB | 29.3 GB | Too big | Get file → | |
| Q6_K | 27.9 GB | 31.7 GB | Too big | Get file → | |
| Q8_0 | 35.5 GB | 40.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (file size 11.64 GB, estimated 13.5 GB memory). For 12 GB VRAM, Q4_K_M (20.03 GB, 22.9 GB memory) is suitable. For 16 GB VRAM, Q5_K_M (23.97 GB, 27.3 GB memory) offers a good balance between quality and memory usage.
What GPU do you need for flux2 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 F16 (0.2 GB file, about 0.7 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (0.2 GB file, about 0.7 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (0.2 GB file, about 0.7 GB in use).
- 12 GB VRAM: the best quant that fits is Q2_K (7.7 GB file, about 9.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q2_K (12.4 GB file, about 14.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (20.0 GB file, about 22.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (27.9 GB file, about 31.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (35.5 GB file, about 40.3 GB in use).
Which flux2 dev quant should you choose?
Q4_K_M is the usual starting point for flux2 dev: it balances file size and quality well. Here it is a 20.0 GB file.
The Q8_0 file is 20.0 GB, about 1.0 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 flux2 dev
How much VRAM does flux2 dev need?
About 22.9 GB at Q4_K_M with an 8K context window. That is the 20.0 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 flux2 dev on an 8 GB GPU?
Yes, with F16: the 0.2 GB file needs about 0.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of flux2 dev GGUF?
It depends on the quant: F16 is 0.2 GB, Q2_K is 7.7 GB, IQ4_XS is 11.1 GB, Q4_0 is 11.6 GB, Q2_K is 12.4 GB, Q3_K_S is 15.6 GB and 15 more.
Where can I download flux2 dev GGUF?
The files are on Hugging Face in the gguf-org/flux2-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 flux2 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 Flux2 dev on 8 GB VRAM?
Yes, using the Q4_0 quantization which requires approximately 13.5 GB of VRAM at 8k context.
Does Flux2 dev support vision tasks?
No, this GGUF release does not include vision capabilities.
What is the file size of the F16 quant?
The F16 quant file is 0.17 GB and requires about 0.7 GB of VRAM at 8k context.