FLUX.2 dev needs about 23.0 GB of memory at Q4_K_M (a 20.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 14 quants, from 12.9 GB (Q2_K) to 64.4 GB (BF16).
FLUX.2 dev – a 32.2 B parameter image generation model in GGUF format
FLUX.2 dev is a 32.2 B parameter model converted to GGUF by city96. It supports image generation and can be used with ComfyUI via the ComfyUI‑GGUF custom node. The model is available in multiple quantizations ranging from Q2_K to BF16.
Good at
- High‑quality image generation
- Supports ComfyUI integration
- Multiple quantization options
Limits
- No vision support in text‑only contexts
- Requires large VRAM for higher quantizations
- License terms apply as original
Best for
- Generating detailed images
- Fine‑tuning on custom datasets
- Running on GPUs with 8 GB+ VRAM
Who it’s for. Developers and researchers who need a flexible, quantized image model for local inference. The model is suitable for users who can manage the memory requirements and adhere to the original license terms.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 12.9 GB | 14.9 GB | Too big | Get file → | |
| Q3_K_S | 15.8 GB | 18.2 GB | Too big | Get file → | |
| Q3_K_M | 16.0 GB | 18.4 GB | Too big | Get file → | |
| Q4_0 | 19.3 GB | 22.1 GB | Too big | Get file → | |
| Q4_K_S | 19.3 GB | 22.1 GB | Too big | Get file → | |
| Q4_K_M | 20.1 GB | 23.0 GB | Too big | Get file → | |
| Q4_1 | 21.3 GB | 24.3 GB | Too big | Get file → | |
| Q5_0 | 23.2 GB | 26.5 GB | Too big | Get file → | |
| Q5_K_S | 23.2 GB | 26.5 GB | Too big | Get file → | |
| Q5_K_M | 24.1 GB | 27.4 GB | Too big | Get file → | |
| Q5_1 | 25.2 GB | 28.7 GB | Too big | Get file → | |
| Q6_K | 27.4 GB | 31.2 GB | Too big | Get file → | |
| Q8_0 | 35.0 GB | 39.7 GB | Too big | Get file → | |
| BF16 | 64.4 GB | 72.7 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (20.08 GB file, ~23 GB memory). For 16 GB VRAM, Q5_K_M (24.06 GB file, ~27.4 GB memory) is suitable. For larger GPUs, consider Q6_K or Q8_0 for higher precision.
What GPU do you need for FLUX.2 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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is Q2_K (12.9 GB file, about 14.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (20.1 GB file, about 23.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (27.4 GB file, about 31.2 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (35.0 GB file, about 39.7 GB in use).
Which FLUX.2 dev quant should you choose?
Q4_K_M is the usual starting point for FLUX.2 dev: it balances file size and quality well. Here it is a 20.1 GB file.
The Q8_0 file is 35.0 GB, about 1.7 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 Q2_K at 12.9 GB, with the quality trade-offs that come with fewer bits. 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about FLUX.2 dev
How much VRAM does FLUX.2 dev need?
About 23.0 GB at Q4_K_M with an 8K context window. That is the 20.1 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.2 dev on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of FLUX.2 dev GGUF?
It depends on the quant: Q2_K is 12.9 GB, Q3_K_S is 15.8 GB, Q3_K_M is 16.0 GB, Q4_0 is 19.3 GB, Q4_K_S is 19.3 GB, Q4_K_M is 20.1 GB and 8 more.
Where can I download FLUX.2 dev GGUF?
The files are on Hugging Face in the city96/FLUX.2-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.2 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.2 dev on 8 GB VRAM?
Use the Q4_K_M quantization; it requires about 23 GB of VRAM at 8k context, so 8 GB VRAM is insufficient.
Is the model free to use?
The model is a direct GGUF conversion; original license terms still apply.
Does the model support vision tasks?
It is an image generation model; no separate vision-only capabilities are provided.