Flux GGUF models
357 GGUF models in the Flux family, quantized by 221 uploaders. Sizes run from 65M to 32.2B parameters. The longest trained context is 256K tokens.
About the Flux GGUF models
Flux is represented on ggufmodels.com by 357 GGUF models, quantized by 221 uploaders on Hugging Face. The most downloaded are FLUX.2 klein 4B, FLUX.2 klein 9B and FLUX.1 dev. Parameter counts run from 65M to 32.2B, and the longest trained context window is 256K tokens.
A Q4_K_M file of a Flux model is between 0.1 to 21.0 GB, which is the quant most people start with. Most files come from unsloth (11), ND911 (11) and wikeeyang (9). The quants you will meet most often are Q8_0 (239), Q6_K (162), Q4_K_M (138) and Q4_0 (123), where the number is how many models offer that quant.
Frequently asked questions
Which Flux GGUF should I download?
The most downloaded Flux GGUF here is FLUX.2 klein 4B. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.
How much VRAM does a Flux model need?
Q4_K_M files of Flux models on this site range from 0.1 to 21.0 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.
Where do Flux GGUF files come from?
The most common quantizers here are unsloth, ND911 and wikeeyang. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.