flux1 needs about 10.5 GB of memory at Q4_0 (a 6.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 15 quants, from 3.4 GB (Q5_K_M) to 9.8 GB (Q6_K).
flux1 is a 4.76B-parameter Flux model in GGUF format, quantized by arcticlatent. Its trained context length is 512 tokens. The repository has 15 quant files, from 3.4 GB (Q5_K_M) to 9.8 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_M | 3.4 GB | 4.1 GB | Fits | Get file → | |
| Q3_K_S | 5.2 GB | 5.9 GB | Fits | Get file → | |
| Q3_K_S | 5.2 GB | 5.9 GB | Fits | Get file → | |
| Q3_K_S | 5.2 GB | 5.9 GB | Fits | Get file → | |
| Q3_K_S | 5.2 GB | 5.9 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 → | |
| Q4_0 | 6.8 GB | 7.5 GB | Tight | Get file → | |
| Q5_K_S | 8.3 GB | 9.0 GB | Too big | Get file → | |
| Q5_0 | 8.3 GB | 9.0 GB | Too big | Get file → | |
| Q5_0 | 8.3 GB | 9.0 GB | Too big | Get file → | |
| Q5_K_S | 8.3 GB | 9.0 GB | Too big | Get file → | |
| Q5_K_S | 8.3 GB | 9.0 GB | Too big | Get file → | |
| Q5_K_M | 8.4 GB | 9.1 GB | Too big | Get file → | |
| Q6_K | 9.8 GB | 10.5 GB | Too big | Get file → |
What GPU do you need for flux1?
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 Q5_K_M (3.4 GB file, about 7.1 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K_S (8.3 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (9.8 GB file, about 13.6 GB in use).
Which flux1 quant should you choose?
Q4_0 (6.8 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is Q5_K_M at 3.4 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about flux1
How much VRAM does flux1 need?
About 10.5 GB at Q4_0 with an 8K context window. That is the 6.8 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 flux1 on an 8 GB GPU?
Yes, with Q5_K_M: the 3.4 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of flux1 GGUF?
It depends on the quant: Q5_K_M is 3.4 GB, Q3_K_S is 5.2 GB, Q3_K_S is 5.2 GB, Q3_K_S is 5.2 GB, Q3_K_S is 5.2 GB, Q3_K_M is 5.4 GB and 9 more.
What context length does flux1 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 flux1 GGUF?
The files are on Hugging Face in the arcticlatent/flux1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.