Patreon
Home / Apps / Research, Comparisons and Experiments / FLUX Models Speed & VRAM Comparison: Every Version and Preci

FLUX Models Speed & VRAM Comparison: Every Version and Precision

FLUX Dev and Schnell in FP16, FP8 and NF4 compared for peak VRAM usage and speed in SwarmUI on an A6000; flux1-dev-fp8 uses 19.33 GB and takes 28 seconds.

comparisonimage generationswarmui
FLUX Models Speed & VRAM Comparison: Every Version and Precision

Highlights

Comprehensive tests of every FLUX model version, including the Schnell-Dev merge and BNB NF4, with FP8 and FP16 T5 text encoders at 1024x1024. Suggests flux1-dev-fp8 for 24 GB GPUs and flux1-dev-bnb-nf4-v2 for 16 GB or less, with links to the auto downloader scripts.

Video tutorial

FLUX.1 vs Midjourney on the Same Prompt: Run FLUX Locally in SwarmUI From 6GB VRAM (2024) · chapters and summary

Where to get it: the full post is free on this Patreon post by Furkan Gözükara (SECourses). Published Aug 15, 2024.

Related

Qwen Image 2512 Training Comparison: The Best Model to Train

Qwen Image 2512 Training Comparison: The Best Model to Train

Qwen Image 2512 is the new king for training: the video compares trained Base, 2512, Edit 2509 and Edit 2511 models and shows a big leap in realism.

NVFP4 With CUDA 13 Tutorial: 100%+ Speed Gain & Quality Comparison

NVFP4 With CUDA 13 Tutorial: 100%+ Speed Gain & Quality Comparison

NVFP4 models run over 100% faster in ComfyUI and SwarmUI with CUDA 13; this full tutorial compares NVFP4 quality on FLUX 2, Z Image Turbo and FLUX 1 in grids.

Qwen Image LoRA Training: Stage 1 Results and Pre-Made Configs

Qwen Image LoRA Training: Stage 1 Results and Pre-Made Configs

Qwen Image LoRA results from more than 35 Stage 1 trainings with SECourses Musubi Tuner; the published pre-made configs train on GPUs with as low as 6 GB.

More in Research, Comparisons and Experiments.