Flux1Dev needs about 6.6 GB of memory at Q4_K_M (a 2.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 8 quants, from 2.9 GB (Q4_K_M) to 12.7 GB (Q8_0).
Flux1Dev is a 11.9B-parameter Flux model in GGUF format, quantized by KazumaSensei. Its trained context length is 512 tokens. The repository has 8 quant files, from 2.9 GB (Q4_K_M) to 12.7 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.9 GB | 3.6 GB | Fits | Get file → | |
| Q8_0 | 5.1 GB | 5.8 GB | Fits | Get file → | |
| Q8_0 | 5.1 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_M | 5.4 GB | 6.1 GB | Fits | Get file → | |
| Q4_0 | 6.8 GB | 7.5 GB | Tight | Get file → | |
| Q6_K | 9.8 GB | 10.5 GB | Too big | Get file → | |
| Q8_0 | 12.7 GB | 13.4 GB | Too big | Get file → | |
| Q8_0 | 12.7 GB | 13.4 GB | Too big | Get file → |
What GPU do you need for Flux1Dev?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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: the best quant that fits is Q4_K_M (2.9 GB file, about 6.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_0 (6.8 GB file, about 10.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (9.8 GB file, about 13.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 16.4 GB in use).
Which Flux1Dev quant should you choose?
Q4_K_M is the usual starting point for Flux1Dev: it balances file size and quality well. Here it is a 2.9 GB file.
The Q8_0 file is 5.1 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Flux1Dev
How much VRAM does Flux1Dev need?
About 6.6 GB at Q4_K_M with an 8K context window. That is the 2.9 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 Flux1Dev on an 8 GB GPU?
Yes, with Q4_K_M: the 2.9 GB file needs about 6.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Flux1Dev GGUF?
It depends on the quant: Q4_K_M is 2.9 GB, Q8_0 is 5.1 GB, Q8_0 is 5.1 GB, Q3_K_M is 5.4 GB, Q4_0 is 6.8 GB, Q6_K is 9.8 GB and 2 more.
What context length does Flux1Dev support?
The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 3.2 GB at 8K and 0.2 GB at 512.
Where can I download Flux1Dev GGUF?
The files are on Hugging Face in the KazumaSensei/Flux1Dev repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.