Ideogram4 GGUF quantized files Model Selection & Quantization Guide To balance generation quality, memory usage, and inference speed, we recommend the following quantization choices for each component: 1. Conditional Diffusion Model ( diffusion/cond/ ) Recommended: Q6 K or Q8 0 Since this model handles the main conditional generation pass, keeping a higher quantization level is key to preserving detail and prompt adherence. 2. Unconditional Diffusion Model ( diffusion/uncond/ ) Recommended: Q4 K or Q5 K Note: Using Q6 K or Q8 0 for the unconditional model is generally unnecessary (overkill) and may slow down generation without providing a noticeable improvement in quality. 3. Text Encoder ( text encoder/ ) Recommended: Q5 K M or Q4 K M These medium sized "K measure" quants offer a good trade off, retaining the text encoder's comprehension capabilities while fitting within reasonable memory limits. General Recommendations for Quantization Types If you are optimizing for inference speed or trying to fit a specific model entirely into VRAM/RAM, keep these rules of thumb in mind: Prefer K variants over 0 and 1 : When choosing between Q4 or Q5 options, always prefer the K variants (e.g.…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy