Guides
Short, practical, and tied to the same data as the rest of the site.
G.01GGUF Q8, Q6, Q5, Q4: which one should you download?FilesG.02FP8, GGUF or 16-bit in ComfyUI: what is the difference?FilesG.03How much VRAM do you need for AI images and video in 2026?BuyingG.04Out of memory in ComfyUI: fixes in the order to try themFixesG.05Text encoders: why T5, UMT5 and Qwen-VL eat your memoryExplainerG.06How much system RAM do you need for ComfyUI?BuyingG.07AMD and Intel GPUs for ComfyUI in 2026GPUsG.08Local AI on a laptop: what the GPU name does not tell youGPUsG.0996 GB of "VRAM" on Strix Halo: what fits, and what it costs youGPUsG.10Why video models need so much more memory than image modelsExplainerG.11INT8, NVFP4, MXFP8: the new model file formats of 2026Files