FLUX.2 Dev GGUF

This is a direct GGUF conversion of . The model files can be used in with the custom node. Place the required model(s) in the following folders: | Type | Name | Location | Download | | ------------ | ----------------------------------- | --------------------------------- | ---------------- | | Main Model | flux2-dev | | GGUF (this repo) | | Text Encoder | Mistral-Small-3.2-24B-Instruct-2506 | | / | | VAE | flux2 VAE | | | - sample size of 1, not strictly representative ### Notes > [!NOTE] > As with Qwen-Image, Q5_K_M, Q4_K_M, Q3_K_M, Q3_K_S and Q2_K have some extra logic as to which blocks to keep in high precision. > > The logic is partially based on guesswork, trial & error, and the graph found in the readme for (which in turn quotes )